diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..cf9c2af8fb05006f6c9db6926094b523acbae4a4
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,137 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+ {%- if json_dict is mapping %}
+ {%- for json_key in json_dict if json_key not in handled_keys %}
+ {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+ {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '' ~ json_key ~ '>' }}
+ {%- else %}
+ {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '' ~ json_key ~ '>' }}
+ {%- endif %}
+ {%- endfor %}
+ {%- endif %}
+{% endmacro %}
+
+{%- if messages[0]["role"] == "system" %}
+ {%- set system_message = messages[0]["content"] %}
+ {%- set loop_messages = messages[1:] %}
+{%- else %}
+ {%- set loop_messages = messages %}
+{%- endif %}
+
+{%- if not tools is defined %}
+ {%- set tools = [] %}
+{%- endif %}
+
+{%- if system_message is defined %}
+ {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+ {%- if tools is iterable and tools | length > 0 %}
+ {{- "<|im_start|>system\nYou are INTELLECT-3, a helpful assistant developed by Prime Intellect, that can interact with a computer to solve tasks." }}
+ {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+ {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
+ {{- "" }}
+ {%- for tool in tools %}
+ {%- if tool.function is defined %}
+ {%- set tool = tool.function %}
+ {%- endif %}
+ {{- "\n\n" ~ tool.name ~ "" }}
+ {%- if tool.description is defined %}
+ {{- '\n' ~ (tool.description | trim) ~ '' }}
+ {%- endif %}
+ {{- '\n' }}
+ {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+ {%- for param_name, param_fields in tool.parameters.properties|items %}
+ {{- '\n' }}
+ {{- '\n' ~ param_name ~ '' }}
+ {%- if param_fields.type is defined %}
+ {{- '\n' ~ (param_fields.type | string) ~ '' }}
+ {%- endif %}
+ {%- if param_fields.description is defined %}
+ {{- '\n' ~ (param_fields.description | trim) ~ '' }}
+ {%- endif %}
+ {%- set handled_keys = ['name', 'type', 'description'] %}
+ {{- render_extra_keys(param_fields, handled_keys) }}
+ {{- '\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {% set handled_keys = ['type', 'properties'] %}
+ {{- render_extra_keys(tool.parameters, handled_keys) }}
+ {{- '\n' }}
+ {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+ {{- render_extra_keys(tool, handled_keys) }}
+ {{- '\n' }}
+ {%- endfor %}
+ {{- "\n" }}
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }}
+{%- endif %}
+{%- if system_message is defined %}
+ {{- '<|im_end|>\n' }}
+{%- else %}
+ {%- if tools is iterable and tools | length > 0 %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- for message in loop_messages %}
+ {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+ {{- '<|im_start|>' + message.role }}
+ {%- if message.content is defined and message.content is string %}
+ {%- if message.reasoning_content is defined -%}
+ {%- if message.reasoning_content -%}
+ {{ '\n' + message.reasoning_content.strip() + '' }}
+ {%- else -%}
+ {{ '\n' }}
+ {%- endif -%}
+ {%- endif -%}
+ {{- '\n' + message.content | trim + '\n' }}
+ {%- endif %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if tool_call.function is defined %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {{- '\n\n\n' }}
+ {%- if tool_call.arguments is defined %}
+ {%- for args_name, args_value in tool_call.arguments|items %}
+ {{- '\n' }}
+ {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+ {{- args_value }}
+ {{- '\n\n' }}
+ {%- endfor %}
+ {%- endif %}
+ {{- '\n' }}
+ {%- endfor %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
+ {{- '<|im_start|>' + message.role }}
+ {%- if message.role == "assistant" and message.reasoning_content is defined %}
+ {%- if message.reasoning_content -%}
+ {{ '\n' + message.reasoning_content.strip() + '' }}
+ {%- else -%}
+ {{ '\n' }}
+ {%- endif -%}
+ {%- if message.content.strip() -%}
+ {{ '\n' + message.content.strip() }}
+ {%- endif -%}
+ {%- else %}
+ {{- '\n' + message.content }}
+ {%- endif %}
+ {{- '<|im_end|>' + '\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
+ {{- '<|im_start|>user\n' }}
+ {%- endif %}
+ {{- '\n' }}
+ {{- message.content }}
+ {{- '\n\n' }}
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
+ {{- '<|im_end|>\n' }}
+ {%- elif loop.last %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- else %}
+ {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+{%- endif %}
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..e87cf6357916fb1a58c0f5ff9cd2d98c19de085e
--- /dev/null
+++ b/config.json
@@ -0,0 +1,410 @@
+{
+ "architectures": [
+ "Glm4MoeForCausalLM"
+ ],
+ "attention_bias": true,
+ "attention_dropout": 0.0,
+ "auto_map": {
+ "AutoConfig": "configuration_glm4_moe.Glm4MoeConfig",
+ "AutoModel": "modeling_glm4_moe.Glm4MoeModel",
+ "AutoModelForCausalLM": "modeling_glm4_moe.Glm4MoeForCausalLM"
+ },
+ "dtype": "bfloat16",
+ "eos_token_id": [
+ 151334,
+ 151329
+ ],
+ "first_k_dense_replace": 1,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 4096,
+ "initializer_range": 0.02,
+ "intermediate_size": 10944,
+ "max_position_embeddings": 131072,
+ "model_type": "glm4_moe",
+ "moe_intermediate_size": 1408,
+ "n_group": 1,
+ "n_routed_experts": 128,
+ "n_shared_experts": 1,
+ "norm_topk_prob": true,
+ "num_attention_heads": 96,
+ "num_experts_per_tok": 8,
+ "num_hidden_layers": 46,
+ "num_key_value_heads": 8,
+ "num_nextn_predict_layers": 1,
+ "pad_token_id": 151329,
+ "partial_rotary_factor": 0.5,
+ "rms_norm_eps": 1e-05,
+ "rope_scaling": null,
+ "rope_theta": 1000000,
+ "routed_scaling_factor": 1.0,
+ "tie_word_embeddings": false,
+ "topk_group": 1,
+ "transformers_version": "4.56.1",
+ "use_cache": false,
+ "use_grouped_mm": true,
+ "use_qk_norm": false,
+ "vocab_size": 151552,
+ "quantization_config": {
+ "config_groups": {
+ "group_0": {
+ "input_activations": {
+ "actorder": null,
+ "block_structure": null,
+ "dynamic": true,
+ "group_size": null,
+ "num_bits": 8,
+ "observer": null,
+ "observer_kwargs": {},
+ "strategy": "token",
+ "symmetric": true,
+ "type": "float"
+ },
+ "output_activations": null,
+ "targets": [
+ "Linear"
+ ],
+ "weights": {
+ "actorder": null,
+ "block_structure": null,
+ "dynamic": false,
+ "group_size": null,
+ "num_bits": 8,
+ "observer": "minmax",
+ "observer_kwargs": {},
+ "strategy": "channel",
+ "symmetric": true,
+ "type": "float"
+ }
+ }
+ },
+ "format": "float-quantized",
+ "ignore": [
+ "model.layers.38.self_attn.k_proj.bias",
+ "model.layers.39.self_attn.v_proj.bias",
+ "model.layers.2.mlp.gate",
+ "model.layers.10.post_attention_layernorm",
+ "model.layers.7.mlp.gate",
+ "model.layers.34.mlp.gate.e_score_correction_bias",
+ "model.layers.32.mlp.gate",
+ "model.layers.38.post_attention_layernorm",
+ "model.layers.1.post_attention_layernorm",
+ "model.layers.17.mlp.gate",
+ "model.layers.41.post_attention_layernorm",
+ "model.layers.41.self_attn.q_proj.bias",
+ "model.layers.27.mlp.gate",
+ "model.layers.40.mlp.gate.e_score_correction_bias",
+ "model.layers.10.mlp.gate.e_score_correction_bias",
+ "model.layers.18.input_layernorm",
+ "model.layers.8.mlp.gate.e_score_correction_bias",
+ "model.layers.17.self_attn.q_proj.bias",
+ "model.layers.1.self_attn.v_proj.bias",
+ "model.layers.22.mlp.gate.e_score_correction_bias",
+ "model.layers.1.mlp.gate.e_score_correction_bias",
+ "model.layers.25.self_attn.k_proj.bias",
+ "model.layers.17.post_attention_layernorm",
+ "model.layers.4.post_attention_layernorm",
+ "model.layers.31.self_attn.k_proj.bias",
+ "model.layers.24.self_attn.v_proj.bias",
+ "model.layers.42.mlp.gate",
+ "model.layers.25.self_attn.v_proj.bias",
+ "model.layers.35.self_attn.k_proj.bias",
+ "model.layers.4.mlp.gate",
+ "model.layers.15.mlp.gate",
+ "model.layers.24.mlp.gate.e_score_correction_bias",
+ "model.layers.23.post_attention_layernorm",
+ "model.layers.2.input_layernorm",
+ "model.layers.30.input_layernorm",
+ "model.layers.41.input_layernorm",
+ "model.layers.31.mlp.gate.e_score_correction_bias",
+ "model.layers.5.self_attn.v_proj.bias",
+ "model.layers.3.mlp.gate.e_score_correction_bias",
+ "model.layers.43.self_attn.k_proj.bias",
+ "model.layers.32.self_attn.q_proj.bias",
+ "model.layers.14.self_attn.q_proj.bias",
+ "model.layers.24.self_attn.q_proj.bias",
+ "model.layers.19.post_attention_layernorm",
+ "model.layers.9.self_attn.k_proj.bias",
+ "model.layers.31.input_layernorm",
+ "model.layers.11.self_attn.q_proj.bias",
+ "model.layers.11.mlp.gate.e_score_correction_bias",
+ "model.layers.15.self_attn.q_proj.bias",
+ "model.layers.35.input_layernorm",
+ "model.layers.14.input_layernorm",
+ "model.layers.19.mlp.gate.e_score_correction_bias",
+ "model.layers.13.mlp.gate",
+ "model.layers.6.self_attn.v_proj.bias",
+ "model.layers.11.mlp.gate",
+ "model.layers.23.self_attn.k_proj.bias",
+ "model.layers.26.self_attn.k_proj.bias",
+ "model.layers.16.self_attn.v_proj.bias",
+ "model.layers.28.mlp.gate.e_score_correction_bias",
+ "model.layers.23.input_layernorm",
+ "model.layers.31.self_attn.q_proj.bias",
+ "model.layers.14.mlp.gate.e_score_correction_bias",
+ "model.norm",
+ "model.layers.8.self_attn.k_proj.bias",
+ "model.layers.28.self_attn.k_proj.bias",
+ "model.layers.9.mlp.gate.e_score_correction_bias",
+ "model.layers.37.self_attn.k_proj.bias",
+ "model.layers.37.post_attention_layernorm",
+ "model.layers.28.post_attention_layernorm",
+ "model.layers.28.self_attn.v_proj.bias",
+ "model.layers.45.self_attn.q_proj.bias",
+ "model.layers.20.input_layernorm",
+ "model.layers.40.self_attn.k_proj.bias",
+ "model.layers.13.post_attention_layernorm",
+ "model.layers.17.self_attn.k_proj.bias",
+ "model.layers.33.mlp.gate.e_score_correction_bias",
+ "model.layers.41.self_attn.k_proj.bias",
+ "model.layers.31.post_attention_layernorm",
+ "model.layers.28.input_layernorm",
+ "model.layers.1.input_layernorm",
+ "model.layers.9.input_layernorm",
+ "model.layers.25.self_attn.q_proj.bias",
+ "model.layers.41.mlp.gate.e_score_correction_bias",
+ "model.layers.21.self_attn.q_proj.bias",
+ "model.layers.40.mlp.gate",
+ "model.layers.32.self_attn.k_proj.bias",
+ "model.layers.17.self_attn.v_proj.bias",
+ "model.layers.29.self_attn.q_proj.bias",
+ "model.layers.36.mlp.gate.e_score_correction_bias",
+ "model.layers.31.self_attn.v_proj.bias",
+ "model.layers.5.mlp.gate.e_score_correction_bias",
+ "model.layers.38.self_attn.v_proj.bias",
+ "model.layers.17.input_layernorm",
+ "model.layers.5.mlp.gate",
+ "model.layers.16.input_layernorm",
+ "model.layers.34.self_attn.q_proj.bias",
+ "model.layers.40.input_layernorm",
+ "model.layers.39.mlp.gate.e_score_correction_bias",
+ "model.layers.18.mlp.gate",
+ "model.layers.32.post_attention_layernorm",
+ "lm_head",
+ "model.layers.4.mlp.gate.e_score_correction_bias",
+ "model.layers.13.self_attn.k_proj.bias",
+ "model.layers.19.input_layernorm",
+ "model.layers.11.self_attn.v_proj.bias",
+ "model.layers.5.self_attn.q_proj.bias",
+ "model.layers.18.self_attn.k_proj.bias",
+ "model.layers.3.self_attn.v_proj.bias",
+ "model.layers.31.mlp.gate",
+ "model.layers.6.self_attn.q_proj.bias",
+ "model.layers.1.mlp.gate",
+ "model.layers.22.self_attn.q_proj.bias",
+ "model.layers.33.post_attention_layernorm",
+ "model.layers.21.self_attn.v_proj.bias",
+ "model.layers.8.self_attn.v_proj.bias",
+ "model.layers.29.self_attn.k_proj.bias",
+ "model.layers.12.self_attn.q_proj.bias",
+ "model.layers.27.self_attn.v_proj.bias",
+ "model.layers.45.self_attn.v_proj.bias",
+ "model.layers.34.self_attn.k_proj.bias",
+ "model.layers.39.self_attn.q_proj.bias",
+ "model.layers.29.self_attn.v_proj.bias",
+ "model.layers.2.post_attention_layernorm",
+ "model.layers.33.input_layernorm",
+ "model.layers.25.post_attention_layernorm",
+ "model.layers.11.self_attn.k_proj.bias",
+ "model.layers.7.input_layernorm",
+ "model.layers.16.self_attn.k_proj.bias",
+ "model.layers.38.mlp.gate.e_score_correction_bias",
+ "model.layers.23.mlp.gate",
+ "model.layers.18.self_attn.q_proj.bias",
+ "model.layers.22.self_attn.k_proj.bias",
+ "model.layers.10.mlp.gate",
+ "model.layers.27.self_attn.k_proj.bias",
+ "model.layers.30.self_attn.k_proj.bias",
+ "model.layers.13.self_attn.v_proj.bias",
+ "model.layers.43.post_attention_layernorm",
+ "model.layers.40.self_attn.q_proj.bias",
+ "model.layers.36.post_attention_layernorm",
+ "model.layers.36.self_attn.q_proj.bias",
+ "model.layers.9.self_attn.v_proj.bias",
+ "model.layers.34.self_attn.v_proj.bias",
+ "model.layers.41.self_attn.v_proj.bias",
+ "model.layers.42.post_attention_layernorm",
+ "model.layers.38.self_attn.q_proj.bias",
+ "model.layers.37.mlp.gate.e_score_correction_bias",
+ "model.layers.45.self_attn.k_proj.bias",
+ "model.layers.32.mlp.gate.e_score_correction_bias",
+ "model.layers.16.mlp.gate",
+ "model.layers.16.mlp.gate.e_score_correction_bias",
+ "model.layers.4.self_attn.v_proj.bias",
+ "model.layers.36.self_attn.k_proj.bias",
+ "model.layers.25.mlp.gate.e_score_correction_bias",
+ "model.layers.20.self_attn.k_proj.bias",
+ "model.layers.12.post_attention_layernorm",
+ "model.layers.29.mlp.gate.e_score_correction_bias",
+ "model.layers.4.input_layernorm",
+ "model.layers.37.mlp.gate",
+ "model.layers.0.input_layernorm",
+ "model.layers.42.self_attn.k_proj.bias",
+ "model.layers.0.self_attn.q_proj.bias",
+ "model.layers.15.self_attn.v_proj.bias",
+ "model.layers.15.input_layernorm",
+ "model.layers.6.post_attention_layernorm",
+ "model.layers.34.post_attention_layernorm",
+ "model.layers.5.input_layernorm",
+ "model.layers.29.post_attention_layernorm",
+ "model.layers.30.mlp.gate",
+ "model.layers.38.input_layernorm",
+ "model.layers.6.input_layernorm",
+ "model.layers.22.post_attention_layernorm",
+ "model.layers.19.self_attn.k_proj.bias",
+ "model.layers.7.self_attn.v_proj.bias",
+ "model.layers.0.self_attn.v_proj.bias",
+ "model.layers.34.input_layernorm",
+ "model.layers.19.self_attn.q_proj.bias",
+ "model.layers.37.input_layernorm",
+ "model.layers.3.self_attn.q_proj.bias",
+ "model.layers.2.self_attn.v_proj.bias",
+ "model.layers.5.post_attention_layernorm",
+ "model.layers.32.input_layernorm",
+ "model.layers.4.self_attn.k_proj.bias",
+ "model.layers.22.self_attn.v_proj.bias",
+ "model.layers.15.post_attention_layernorm",
+ "model.layers.10.self_attn.v_proj.bias",
+ "model.layers.9.mlp.gate",
+ "model.layers.7.self_attn.k_proj.bias",
+ "model.layers.32.self_attn.v_proj.bias",
+ "model.layers.33.self_attn.q_proj.bias",
+ "model.layers.27.mlp.gate.e_score_correction_bias",
+ "model.layers.7.post_attention_layernorm",
+ "model.layers.37.self_attn.v_proj.bias",
+ "model.layers.29.mlp.gate",
+ "model.layers.14.mlp.gate",
+ "model.layers.42.self_attn.q_proj.bias",
+ "model.layers.28.mlp.gate",
+ "model.layers.22.mlp.gate",
+ "model.layers.14.self_attn.v_proj.bias",
+ "model.layers.26.self_attn.q_proj.bias",
+ "model.layers.44.self_attn.q_proj.bias",
+ "model.layers.21.input_layernorm",
+ "model.layers.27.post_attention_layernorm",
+ "model.layers.24.self_attn.k_proj.bias",
+ "model.layers.19.self_attn.v_proj.bias",
+ "model.layers.26.self_attn.v_proj.bias",
+ "model.layers.45.mlp.gate.e_score_correction_bias",
+ "model.layers.42.input_layernorm",
+ "model.layers.15.self_attn.k_proj.bias",
+ "model.layers.6.mlp.gate",
+ "model.layers.33.self_attn.v_proj.bias",
+ "model.layers.44.self_attn.k_proj.bias",
+ "model.layers.7.mlp.gate.e_score_correction_bias",
+ "model.layers.45.mlp.gate",
+ "model.layers.12.input_layernorm",
+ "model.layers.24.post_attention_layernorm",
+ "model.layers.35.self_attn.v_proj.bias",
+ "model.layers.35.mlp.gate",
+ "model.layers.17.mlp.gate.e_score_correction_bias",
+ "model.layers.8.input_layernorm",
+ "model.layers.30.self_attn.q_proj.bias",
+ "model.layers.26.post_attention_layernorm",
+ "model.layers.8.self_attn.q_proj.bias",
+ "model.layers.3.post_attention_layernorm",
+ "model.layers.12.mlp.gate.e_score_correction_bias",
+ "model.layers.8.post_attention_layernorm",
+ "model.layers.8.mlp.gate",
+ "model.layers.6.mlp.gate.e_score_correction_bias",
+ "model.layers.33.self_attn.k_proj.bias",
+ "model.layers.3.self_attn.k_proj.bias",
+ "model.layers.29.input_layernorm",
+ "model.layers.42.self_attn.v_proj.bias",
+ "model.layers.35.self_attn.q_proj.bias",
+ "model.layers.2.mlp.gate.e_score_correction_bias",
+ "model.layers.13.input_layernorm",
+ "model.layers.6.self_attn.k_proj.bias",
+ "model.layers.16.post_attention_layernorm",
+ "model.embed_tokens",
+ "model.layers.23.self_attn.q_proj.bias",
+ "model.layers.12.self_attn.v_proj.bias",
+ "model.layers.13.self_attn.q_proj.bias",
+ "model.layers.9.self_attn.q_proj.bias",
+ "model.layers.20.mlp.gate",
+ "model.layers.39.post_attention_layernorm",
+ "model.layers.21.self_attn.k_proj.bias",
+ "model.layers.18.post_attention_layernorm",
+ "model.layers.39.mlp.gate",
+ "model.layers.35.mlp.gate.e_score_correction_bias",
+ "model.layers.43.mlp.gate.e_score_correction_bias",
+ "model.layers.13.mlp.gate.e_score_correction_bias",
+ "model.layers.44.self_attn.v_proj.bias",
+ "model.layers.20.post_attention_layernorm",
+ "model.layers.18.self_attn.v_proj.bias",
+ "model.layers.4.self_attn.q_proj.bias",
+ "model.layers.10.input_layernorm",
+ "model.layers.33.mlp.gate",
+ "model.layers.1.self_attn.q_proj.bias",
+ "model.layers.30.mlp.gate.e_score_correction_bias",
+ "model.layers.0.self_attn.k_proj.bias",
+ "model.layers.2.self_attn.q_proj.bias",
+ "model.layers.44.post_attention_layernorm",
+ "model.layers.36.input_layernorm",
+ "model.layers.40.self_attn.v_proj.bias",
+ "model.layers.35.post_attention_layernorm",
+ "model.layers.14.self_attn.k_proj.bias",
+ "model.layers.37.self_attn.q_proj.bias",
+ "model.layers.16.self_attn.q_proj.bias",
+ "model.layers.44.mlp.gate",
+ "model.layers.27.input_layernorm",
+ "model.layers.44.mlp.gate.e_score_correction_bias",
+ "model.layers.36.self_attn.v_proj.bias",
+ "model.layers.39.self_attn.k_proj.bias",
+ "model.layers.12.self_attn.k_proj.bias",
+ "model.layers.40.post_attention_layernorm",
+ "model.layers.25.mlp.gate",
+ "model.layers.24.input_layernorm",
+ "model.layers.38.mlp.gate",
+ "model.layers.11.post_attention_layernorm",
+ "model.layers.43.mlp.gate",
+ "model.layers.11.input_layernorm",
+ "model.layers.44.input_layernorm",
+ "model.layers.43.input_layernorm",
+ "model.layers.20.mlp.gate.e_score_correction_bias",
+ "model.layers.2.self_attn.k_proj.bias",
+ "model.layers.10.self_attn.k_proj.bias",
+ "model.layers.25.input_layernorm",
+ "model.layers.43.self_attn.v_proj.bias",
+ "model.layers.24.mlp.gate",
+ "model.layers.26.input_layernorm",
+ "model.layers.23.mlp.gate.e_score_correction_bias",
+ "model.layers.30.self_attn.v_proj.bias",
+ "model.layers.19.mlp.gate",
+ "model.layers.28.self_attn.q_proj.bias",
+ "model.layers.3.mlp.gate",
+ "model.layers.9.post_attention_layernorm",
+ "model.layers.21.post_attention_layernorm",
+ "model.layers.7.self_attn.q_proj.bias",
+ "model.layers.45.input_layernorm",
+ "model.layers.12.mlp.gate",
+ "model.layers.14.post_attention_layernorm",
+ "model.layers.5.self_attn.k_proj.bias",
+ "model.layers.42.mlp.gate.e_score_correction_bias",
+ "model.layers.43.self_attn.q_proj.bias",
+ "model.layers.20.self_attn.q_proj.bias",
+ "model.layers.18.mlp.gate.e_score_correction_bias",
+ "model.layers.1.self_attn.k_proj.bias",
+ "model.layers.21.mlp.gate",
+ "model.layers.26.mlp.gate.e_score_correction_bias",
+ "model.layers.30.post_attention_layernorm",
+ "model.layers.20.self_attn.v_proj.bias",
+ "model.layers.26.mlp.gate",
+ "model.layers.23.self_attn.v_proj.bias",
+ "model.layers.21.mlp.gate.e_score_correction_bias",
+ "model.layers.34.mlp.gate",
+ "model.layers.39.input_layernorm",
+ "model.layers.3.input_layernorm",
+ "model.layers.0.post_attention_layernorm",
+ "model.layers.45.post_attention_layernorm",
+ "model.layers.22.input_layernorm",
+ "model.layers.15.mlp.gate.e_score_correction_bias",
+ "model.layers.10.self_attn.q_proj.bias",
+ "model.layers.27.self_attn.q_proj.bias",
+ "model.layers.41.mlp.gate",
+ "model.layers.36.mlp.gate"
+ ],
+ "quant_method": "compressed-tensors",
+ "quantization_status": "compressed"
+ }
+}
\ No newline at end of file
diff --git a/model-00001-of-00048.safetensors b/model-00001-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2a9e7178a2b9069ab59f0cd600cef8df6be0b327
--- /dev/null
+++ b/model-00001-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55adfab01177e353fee3a89bbfa34c684147aff3a773b63c41166d13fe309ae0
+size 3072488656
diff --git a/model-00002-of-00048.safetensors b/model-00002-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..635863424a452e3969045c737ff264b8571935ba
--- /dev/null
+++ b/model-00002-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:798634f9900c31c9a49b83b91e6080c0b09ebd255f9e79ca72f145df819a66e6
+size 2452152408
diff --git a/model-00003-of-00048.safetensors b/model-00003-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4ff953397d809f759b1bb28fb86f655f9b1ebfde
--- /dev/null
+++ b/model-00003-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6167cfde28532b5f968e5ec02a16d490d58a8cf56745a0ab518473d3eaf8db72
+size 2872229192
diff --git a/model-00005-of-00048.safetensors b/model-00005-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7b87d5cc2e54d964738e6d94327c04525f3274ed
--- /dev/null
+++ b/model-00005-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee2216cddde3f458ba74348f9dcd6525de7facacbbcfb13bb26ea2bc980edc19
+size 2236605352
diff --git a/model-00006-of-00048.safetensors b/model-00006-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..234e8a12502c59e37f973c7f7f09399f66610875
--- /dev/null
+++ b/model-00006-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:970fbfed0f6e9a77fa599af58e39a1118df735bff63e1a3dc92e85557ec6e085
+size 2236605352
diff --git a/model-00007-of-00048.safetensors b/model-00007-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f92f0db40dc7f9f05516c96a0a0be0bc9c909bc3
--- /dev/null
+++ b/model-00007-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e40d529fafb6f699c366c903fd11aca8bfda4e37db5f15a5d7663d5d0db195a
+size 2236605352
diff --git a/model-00008-of-00048.safetensors b/model-00008-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..db37596e6e879e282934b55d321fbdae8113e067
--- /dev/null
+++ b/model-00008-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:334efb1102f03ecddc5c1d7a2652cc7761d8c17c8f26c4fee03bb530f3486109
+size 2236605352
diff --git a/model-00009-of-00048.safetensors b/model-00009-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fcb18b1e458e3509c3b1459346f83135875fd119
--- /dev/null
+++ b/model-00009-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c52e1eb34e8ed7bc475bff6cbf6deef5ffd0c6e1490632b5ab16b336317b025
+size 2236605352
diff --git a/model-00010-of-00048.safetensors b/model-00010-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c57583bd1a882a3240a78a6c728e46df51fc9280
--- /dev/null
+++ b/model-00010-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d95b89703140ecf9618e85ba727fccc4015fcbccc08666259806fbb2d3813295
+size 2236605352
diff --git a/model-00012-of-00048.safetensors b/model-00012-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0ac405c1cc2203d32628d6acd107b1e13e64e2fd
--- /dev/null
+++ b/model-00012-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e704bc2c8ca6c0e1fbd22c9d68fc9825079b10ed7f7b4237d585ea322c94b5f7
+size 2236605472
diff --git a/model-00014-of-00048.safetensors b/model-00014-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fb41266117f52bd050041602a02b64532d513d3e
--- /dev/null
+++ b/model-00014-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f16306a7b8b7bc98246cb836be373cf1fe386115423815222ee28503392cbe3a
+size 2236606128
diff --git a/model-00015-of-00048.safetensors b/model-00015-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..43912e9c200b3b9cbe2982300e349b89d5ab72c1
--- /dev/null
+++ b/model-00015-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057935deef278c3601f1b30ebe5a3c676397b891f9dddce025f6d8ceb4bddc18
+size 2236606128
diff --git a/model-00016-of-00048.safetensors b/model-00016-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..edc367e7693e4e5602715fc27bf3e5d863f96df3
--- /dev/null
+++ b/model-00016-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:740ec4bb5a8d09fe1b58160019cb5ffd772b30bad5c91c569b08e97f591762e1
+size 2236606128
diff --git a/model-00017-of-00048.safetensors b/model-00017-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4c971d2d4f20c3040fbcdbcd7fc92ab0e087ed45
--- /dev/null
+++ b/model-00017-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15464d80977b3334c76bc1ed1ced222f26b8e167b38478a9b6f7f45ebf10d47c
+size 2236606128
diff --git a/model-00018-of-00048.safetensors b/model-00018-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f8c51f8be33a77b8f38ba73373691c3ba6cd7a75
--- /dev/null
+++ b/model-00018-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8387dfa034f582d721819a4df41ff6b05e36dcbf3d3aaa69587680dc1b359565
+size 2236606128
diff --git a/model-00019-of-00048.safetensors b/model-00019-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2a7e8c3277516f874360e05b4c86aca89a4ead30
--- /dev/null
+++ b/model-00019-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8901d3623d3d14bee554760655c054b40b361fa8f10a0410155ac12d5eeb9a
+size 2236606128
diff --git a/model-00020-of-00048.safetensors b/model-00020-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c3db45a0883e8656ce28ac46491be837f89e2c07
--- /dev/null
+++ b/model-00020-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e455e8efcb2f42a51c7d43759200bbb934a9bd9fc565b17ec1466cb0129016
+size 2236606128
diff --git a/model-00021-of-00048.safetensors b/model-00021-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b5fb46d6dcc8fb035d933888c30f4ef2065de556
--- /dev/null
+++ b/model-00021-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53d145346d4cff834bea09f2a7992af6b46099ea56cec55ee11da26c8f371085
+size 2236606128
diff --git a/model-00022-of-00048.safetensors b/model-00022-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4a29fdd2019a98204991ae2d62defed1aea195c5
--- /dev/null
+++ b/model-00022-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3cd0931c1f81fae110518a75f005e2c59fb07faa3925c401fbcfcd2c9f876aa
+size 2236606128
diff --git a/model-00024-of-00048.safetensors b/model-00024-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d94bb37c98bec15b9d5d71f4cea07aa952f90786
--- /dev/null
+++ b/model-00024-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee52fe916f24c4165e44eeeb1cc0a13e56d76c9828c4cf386126d3e818801f7
+size 2236606128
diff --git a/model-00025-of-00048.safetensors b/model-00025-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..295646ca30a030353aff028082cd4d363ebec3a5
--- /dev/null
+++ b/model-00025-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f707eafa915d8748a36f2a80e031947ea7d5bff237d80806030323e6283124
+size 2236606128
diff --git a/model-00026-of-00048.safetensors b/model-00026-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..036167b451027e76e52dcbd906c62e1c02f17420
--- /dev/null
+++ b/model-00026-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bd5138f8c02a148fd745e94dcc95c2539a6c12ba6b20105949fb28c40d1a39e
+size 2236606128
diff --git a/model-00027-of-00048.safetensors b/model-00027-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c98ade114a41b21dcd735f9494a33f0a191c97a0
--- /dev/null
+++ b/model-00027-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e48d12df4347a322209dc35f23f45bbf5f50ffd263a19ae99e9977b50d3cdfe
+size 2236606128
diff --git a/model-00028-of-00048.safetensors b/model-00028-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..71fbc74d017a6338b9f181aa070560d858325355
--- /dev/null
+++ b/model-00028-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddce34397a046c451a9fc9ecb67452559d698906056d59d0039979aeb00692b4
+size 2236606128
diff --git a/model-00029-of-00048.safetensors b/model-00029-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a2bff740ab3d8b13d6aef98a35348181704b6abf
--- /dev/null
+++ b/model-00029-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9630923a1667fa9489d16eeacf9ba96a09cf456c3e796fef6efea004594be2e2
+size 2236606128
diff --git a/model-00030-of-00048.safetensors b/model-00030-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5a9cc086b25a9f1cd5fd7d6a9f67e6f10968a32d
--- /dev/null
+++ b/model-00030-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1f9cd1023158121d5a62fc37ee405f3e9a626fc206fc2557282cd452ffeb85
+size 2236606128
diff --git a/model-00031-of-00048.safetensors b/model-00031-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9403f3849d57972c9780f3fb37de0cb55e3052ff
--- /dev/null
+++ b/model-00031-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e87059a88d584d1092202b4b383076e69edf584e0bc0e0e0328c8f61ab7142
+size 2236606128
diff --git a/model-00032-of-00048.safetensors b/model-00032-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..755bdbbcb4e6b848e3418c9bcd4747b0bb2d1b71
--- /dev/null
+++ b/model-00032-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eec234dab476f73af642a0ed37d39b4334bc1e15a6489392cadce02e24617e8
+size 2236606128
diff --git a/model-00033-of-00048.safetensors b/model-00033-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2e1b1f2b782cf93c5cd8a7cae275400274dec9e2
--- /dev/null
+++ b/model-00033-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4123cebc648af42d2eb830411e485516ba19652060e239bb561243ea3efca1d9
+size 2236606128
diff --git a/model-00034-of-00048.safetensors b/model-00034-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5f6312484284c28e4f5ae71134d4ad4700af49cd
--- /dev/null
+++ b/model-00034-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1511a6dd9536861c4d58deaa1e31006a932b35ec529cbee216972a3ef624fd9
+size 2236606128
diff --git a/model-00035-of-00048.safetensors b/model-00035-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ab7ff060808f59e04b1187311ba014280166487c
--- /dev/null
+++ b/model-00035-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b047ab2e885e46e0177ba0480c714ea853f33725c91b96b3426bfa3b80d1f6d
+size 2236606128
diff --git a/model-00036-of-00048.safetensors b/model-00036-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1fdf47e4f0ff534ace582598782842353481cde9
--- /dev/null
+++ b/model-00036-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ebc0cbebf7cfd8416e77dab0002bcda6d968e8f634bbc5bdec3f77b52238d91
+size 2236606128
diff --git a/model-00037-of-00048.safetensors b/model-00037-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a6737dbde009ad8d23bf7d77ea40f2904e7799be
--- /dev/null
+++ b/model-00037-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4316be65f3858fc7ebe0f8805bf97dca386d50218d6ccd5b0dc5b1c943f6fcb2
+size 2236606128
diff --git a/model-00038-of-00048.safetensors b/model-00038-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6f25669cf2807c74bab431274a6c8768d4e9e14c
--- /dev/null
+++ b/model-00038-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92979465dca1192272534067632c89a6f1dca20b86737cc8ce4b01fa87cdbc2b
+size 2236606128
diff --git a/model-00039-of-00048.safetensors b/model-00039-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b1e0f8f9d80e8da0983989d34affc2c4f688b9f6
--- /dev/null
+++ b/model-00039-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d86f4aef7d11ea69c4519ebb6f6ee908b3dcdba6038a5eb5fd33fe6a3a21cf
+size 2236606128
diff --git a/model-00040-of-00048.safetensors b/model-00040-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f3188c4f1823be3816e3848eff0de303d7915ab3
--- /dev/null
+++ b/model-00040-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:038980af7c3e713b1accca80251925de33e19a33538995bebe2a855103dc8d9e
+size 2236606128
diff --git a/model-00041-of-00048.safetensors b/model-00041-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ffd75dd9b711cba992d45b219f747044d6e34548
--- /dev/null
+++ b/model-00041-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69138266242069b6bf7b2b3217dc5e68c7f25f280079e702c9493934051bff21
+size 2236606128
diff --git a/model-00042-of-00048.safetensors b/model-00042-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f2beaa50de408030795e4599a9ccf64f3d964a27
--- /dev/null
+++ b/model-00042-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3978b44fc97eacbfa5c3c4229402ef180d88ffa0d79ccec045b2ed6ed82f32f6
+size 2236606128
diff --git a/model-00043-of-00048.safetensors b/model-00043-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..38e161cd3f16b3e222f80ec80855a3cca2e25586
--- /dev/null
+++ b/model-00043-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e700c7dedc35c6456d3856f398ccfaf3a7f57dcc7ddf6a5fa3c2e2952ddad52d
+size 2236606128
diff --git a/model-00044-of-00048.safetensors b/model-00044-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d6514653dab491763e70e50efca7494e6982e2ef
--- /dev/null
+++ b/model-00044-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cadbc7e58745f111ff6aba750a49687fcd649d5b20ec8547452d4dfdcada81ef
+size 2236606128
diff --git a/model-00045-of-00048.safetensors b/model-00045-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5b57b1557fd2919b79b5697428f9f6118f9058d8
--- /dev/null
+++ b/model-00045-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:268fd64493665f69bf502ba98ab5f202b11a515ef6e0f0caf1ae6ff75bcb66c2
+size 2236606128
diff --git a/model-00046-of-00048.safetensors b/model-00046-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..61bb15a4a01a0be557c8da1ac7f81d2cf479861a
--- /dev/null
+++ b/model-00046-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66202bc7bd5a62a7d9c29b68e9ed61588cfd8bf6e704e897890aaf1e73db45e
+size 2236606128
diff --git a/model-00047-of-00048.safetensors b/model-00047-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b1a939a3f3fde79e8182448c7945236a4249908d
--- /dev/null
+++ b/model-00047-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb61c7bc8186357ebe539bf7c4199efa504cec7b71f4f6c9a86fa7cd2e2fb26
+size 2236606128
diff --git a/model-00048-of-00048.safetensors b/model-00048-of-00048.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c4a080a06155e8cdbf1ce52c6a54942b727aa6a9
--- /dev/null
+++ b/model-00048-of-00048.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87d91bf8af67f3f73756c42e8c5e53782f64983d9e566ede5449569c64c05c12
+size 1479276336
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..d86449614350a4708f5f38e554d499ee0be25c00
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,35534 @@
+{
+ "weight_map": {
+ "model.layers.37.mlp.experts.0.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.0.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.0.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.0.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.1.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.1.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.1.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.1.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.10.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.10.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.10.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.10.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.100.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.100.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.100.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.100.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.101.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.101.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.101.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.101.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.102.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.102.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.102.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.102.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.103.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.103.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.103.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.103.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.104.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.104.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.104.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.104.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.105.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.105.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.105.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.105.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.106.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.106.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.106.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.106.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.107.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.107.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.107.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.107.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.108.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.108.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.108.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.108.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.109.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.109.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.109.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.109.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.11.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.11.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.11.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.11.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.110.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.110.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.110.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.110.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.111.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.111.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.111.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.111.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.112.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.112.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.112.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.112.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.113.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.113.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.113.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.113.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.114.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.114.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.114.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.114.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.115.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.115.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.115.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.115.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.116.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.116.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.116.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.116.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.117.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.117.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.117.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.117.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.118.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.118.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.118.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.118.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.119.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.119.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.119.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.119.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.12.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.12.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.12.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.12.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.120.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.120.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.120.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.120.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.121.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.121.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.121.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.121.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.122.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.122.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.122.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.122.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.123.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.123.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.123.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.123.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.124.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.124.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.124.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.124.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.125.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.125.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.125.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.125.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.126.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.126.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.126.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.126.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.127.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.127.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.127.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.127.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.13.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.13.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.13.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.13.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.14.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.14.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.14.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.14.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.15.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.15.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.15.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.15.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.16.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.16.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.16.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.16.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.17.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.17.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.17.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.17.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.18.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.18.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.18.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.18.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.19.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.19.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.19.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.19.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.2.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.2.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.2.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.2.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.20.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.20.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.20.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.20.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.21.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.21.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.21.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.21.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.22.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.22.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.22.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.22.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.23.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.23.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.23.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.23.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.24.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.24.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.24.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.24.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.25.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.25.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.25.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.25.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.26.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.26.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.26.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.26.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.27.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.27.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.27.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.27.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.28.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.28.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.28.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.28.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.29.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.29.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.29.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.29.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.3.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.3.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.3.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.3.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.30.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.30.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.30.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.30.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.31.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.31.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.31.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.31.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.32.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.32.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.32.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.32.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.33.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.33.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.33.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.33.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.34.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.34.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.34.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.34.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.35.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.35.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.35.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.35.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.36.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.36.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.36.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.36.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.37.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.37.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.37.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.37.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.38.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.38.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.38.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.38.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.39.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.39.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.39.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.39.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.4.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.4.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.4.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.4.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.40.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.40.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.40.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.40.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.41.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.41.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.41.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.41.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.42.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.42.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.42.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.42.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.43.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.43.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.43.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.43.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.44.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.44.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.44.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.44.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.45.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.45.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.45.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.45.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.46.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.46.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.46.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.46.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.47.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.47.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.47.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.47.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.48.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.48.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.48.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.48.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.49.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.49.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.49.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.49.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.5.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.5.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.5.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.5.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.50.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.50.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.50.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.50.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.51.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.51.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.51.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.51.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.52.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.52.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.52.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.52.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.53.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.53.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.53.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.53.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.54.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.54.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.54.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.54.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.55.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.55.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.55.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.55.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.56.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.56.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.56.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.56.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.57.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.57.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.57.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.57.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.58.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.58.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.58.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.58.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.59.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.59.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.59.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.59.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.6.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.6.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.6.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.6.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.60.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.60.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.60.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.60.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.61.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.61.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.61.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.61.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.62.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.62.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.62.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.62.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.63.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.63.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.63.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.63.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.64.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.64.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.64.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.64.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.65.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.65.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.65.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.65.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.66.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.66.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.66.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.66.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.67.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.67.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.67.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.67.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.68.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.68.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.68.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.68.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.69.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.69.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.69.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.69.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.7.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.7.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.7.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.7.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.70.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.70.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.70.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.70.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.71.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.71.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.71.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.71.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.72.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.72.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.72.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.72.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.73.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.73.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.73.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.73.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.74.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.74.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.74.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.74.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.75.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.75.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.75.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.75.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.76.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.76.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.76.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.76.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.77.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.77.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.77.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.77.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.78.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.78.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.78.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.78.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.79.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.79.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.79.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.79.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.8.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.8.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.8.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.8.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.80.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.80.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.80.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.80.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.81.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.81.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.81.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.81.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.82.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.82.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.82.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.82.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.83.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.83.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.83.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.83.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.84.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.84.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.84.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.84.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.85.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.85.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.85.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.85.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.86.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.86.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.86.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.86.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.87.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.87.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.87.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.87.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.88.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.88.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.88.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.88.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.89.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.89.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.89.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.89.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.9.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.9.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.9.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.9.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.90.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.90.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.90.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.90.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.91.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.91.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.91.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.91.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.92.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.92.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.92.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.92.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.93.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.93.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.93.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.93.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.94.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.94.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.94.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.94.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.95.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.95.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.95.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.95.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.96.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.96.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.96.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.96.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.97.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.97.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.97.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.97.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.98.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.98.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.98.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.98.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.99.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.99.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.99.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.37.mlp.experts.99.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.0.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.1.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.10.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.100.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.100.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.101.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.101.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.102.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.102.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.103.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.103.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.104.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.104.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.105.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.105.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.106.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.106.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.107.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.107.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.108.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.108.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.109.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.109.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.11.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.110.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.110.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.111.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.111.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.112.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.112.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.113.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.113.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.114.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.114.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.115.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.115.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.116.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.116.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.117.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.117.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.118.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.118.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.119.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.119.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.12.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.120.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.120.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.121.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.121.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.122.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.122.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.123.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.123.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.124.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.124.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.125.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.125.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.126.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.126.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.127.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.127.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.13.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.14.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.15.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.16.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.17.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.18.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.19.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.2.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.20.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.21.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.22.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.23.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.24.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.25.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.26.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.27.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.28.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.29.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.3.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.30.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.31.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.32.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.33.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.34.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.35.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.36.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.37.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.38.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.39.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.4.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.40.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.41.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.42.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.43.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.44.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.45.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.46.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.47.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.48.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.49.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.5.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.50.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.51.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.52.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.53.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.54.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.55.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.56.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.57.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.58.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.59.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.6.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.60.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.61.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.62.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.63.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.64.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.64.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.65.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.65.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.66.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.66.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.67.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.67.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.68.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.68.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.69.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.69.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.7.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.70.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.70.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.71.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.71.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.72.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.72.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.73.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.73.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.74.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.74.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.75.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.75.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.76.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.76.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.77.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.77.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.78.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.78.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.79.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.79.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.8.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.80.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.80.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.81.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.81.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.82.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.82.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.83.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.83.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.84.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.84.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.85.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.85.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.86.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.86.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.87.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.87.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.88.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.88.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.89.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.89.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.9.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.90.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.90.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.91.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.91.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.92.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.92.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.93.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.93.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.94.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.94.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.95.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.95.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.96.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.96.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.97.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.97.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.98.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.98.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.99.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.experts.99.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.gate.e_score_correction_bias": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.gate.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.shared_experts.down_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.shared_experts.gate_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00040-of-00048.safetensors",
+ "model.layers.38.mlp.shared_experts.up_proj.weight_scale": "model-00040-of-00048.safetensors",
+ "model.layers.19.mlp.experts.0.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.0.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.0.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.0.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.1.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.1.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.1.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.1.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.10.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.10.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.10.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.10.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.100.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.100.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.100.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.100.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.101.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.101.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.101.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.101.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.102.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.102.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.102.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.102.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.103.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.103.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.103.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.103.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.104.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.104.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.104.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.104.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.105.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.105.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.105.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.105.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.106.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.106.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.106.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.106.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.107.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.107.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.107.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.107.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.108.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.108.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.108.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.108.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.109.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.109.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.109.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.109.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.11.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.11.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.11.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.11.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.110.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.110.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.110.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.110.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.111.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.111.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.111.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.111.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.112.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.112.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.112.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.112.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.113.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.113.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.113.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.113.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.114.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.114.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.114.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.114.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.115.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.115.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.115.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.115.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.116.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.116.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.116.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.116.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.117.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.117.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.117.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.117.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.118.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.118.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.118.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.118.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.119.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.119.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.119.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.119.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.12.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.12.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.12.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.12.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.120.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.120.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.120.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.120.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.121.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.121.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.121.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.121.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.122.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.122.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.122.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.122.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.123.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.123.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.123.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.123.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.124.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.124.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.124.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.124.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.125.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.125.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.125.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.125.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.126.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.126.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.126.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.126.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.127.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.127.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.127.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.127.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.13.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.13.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.13.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.13.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.14.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.14.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.14.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.14.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.15.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.15.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.15.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.15.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.16.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.16.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.16.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.16.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.17.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.17.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.17.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.17.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.18.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.18.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.18.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.18.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.19.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.19.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.19.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.19.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.2.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.2.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.2.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.2.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.20.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.20.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.20.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.20.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.21.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.21.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.21.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.21.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.22.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.22.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.22.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.22.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.23.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.23.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.23.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.23.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.24.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.24.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.24.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.24.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.25.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.25.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.25.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.25.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.26.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.26.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.26.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.26.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.27.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.27.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.27.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.27.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.28.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.28.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.28.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.28.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.29.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.29.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.29.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.29.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.3.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.3.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.3.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.3.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.30.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.30.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.30.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.30.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.31.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.31.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.31.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.31.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.32.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.32.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.32.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.32.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.33.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.33.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.33.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.33.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.34.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.34.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.34.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.34.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.35.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.35.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.35.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.35.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.36.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.36.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.36.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.36.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.37.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.37.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.37.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.37.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.38.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.38.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.38.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.38.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.39.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.39.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.39.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.39.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.4.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.4.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.4.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.4.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.40.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.40.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.40.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.40.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.41.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.41.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.41.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.41.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.42.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.42.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.42.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.42.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.43.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.43.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.43.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.43.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.44.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.44.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.44.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.44.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.45.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.45.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.45.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.45.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.46.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.46.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.46.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.46.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.47.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.47.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.47.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.47.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.48.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.48.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.48.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.48.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.49.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.49.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.49.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.49.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.5.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.5.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.5.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.5.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.50.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.50.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.50.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.50.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.51.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.51.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.51.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.51.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.52.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.52.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.52.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.52.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.53.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.53.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.53.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.53.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.54.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.54.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.54.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.54.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.55.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.55.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.55.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.55.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.56.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.56.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.56.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.56.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.57.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.57.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.57.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.57.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.58.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.58.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.58.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.58.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.59.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.59.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.59.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.59.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.6.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.6.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.6.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.6.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.60.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.60.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.60.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.60.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.61.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.61.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.61.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.61.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.62.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.62.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.62.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.62.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.63.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.63.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.63.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.63.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.64.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.64.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.64.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.64.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.65.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.65.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.65.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.65.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.66.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.66.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.66.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.66.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.67.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.67.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.67.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.67.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.68.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.68.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.68.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.68.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.69.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.69.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.69.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.69.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.7.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.7.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.7.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.7.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.70.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.70.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.70.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.70.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.71.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.71.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.71.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.71.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.72.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.72.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.72.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.72.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.73.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.73.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.73.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.73.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.74.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.74.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.74.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.74.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.75.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.75.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.75.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.75.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.76.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.76.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.76.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.76.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.77.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.77.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.77.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.77.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.78.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.78.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.78.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.78.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.79.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.79.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.79.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.79.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.8.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.8.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.8.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.8.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.80.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.80.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.80.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.80.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.81.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.81.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.81.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.81.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.82.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.82.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.82.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.82.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.83.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.83.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.83.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.83.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.84.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.84.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.84.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.84.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.85.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.85.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.85.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.85.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.86.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.86.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.86.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.86.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.87.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.87.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.87.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.87.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.88.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.88.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.88.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.88.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.89.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.89.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.89.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.89.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.9.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.9.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.9.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.9.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.90.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.90.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.90.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.90.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.91.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.91.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.91.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.91.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.92.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.92.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.92.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.92.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.93.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.93.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.93.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.93.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.94.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.94.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.94.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.94.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.95.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.95.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.95.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.95.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.96.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.96.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.96.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.96.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.97.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.97.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.97.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.97.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.98.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.98.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.98.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.98.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.99.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.99.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.99.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.19.mlp.experts.99.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.0.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.1.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.10.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.100.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.101.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.102.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.103.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.104.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.105.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.106.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.107.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.108.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.109.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.11.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.110.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.111.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.112.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.113.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.114.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.115.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.116.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.117.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.118.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.119.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.12.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.120.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.121.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.122.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.123.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.124.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.125.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.126.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.127.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.13.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.14.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.15.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.16.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.17.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.18.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.19.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.2.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.20.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.21.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.22.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.23.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.24.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.25.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.26.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.27.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.28.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.29.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.3.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.30.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.31.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.32.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.33.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.34.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.35.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.36.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.37.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.38.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.39.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.4.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.40.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.41.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.42.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.43.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.44.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.45.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.46.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.47.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.48.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.49.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.5.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.50.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.51.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.52.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.53.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.54.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.55.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.56.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.57.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.58.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.59.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.6.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.60.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.61.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.62.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.63.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.64.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.65.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.66.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.67.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.68.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.69.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.7.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.70.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.71.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.72.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.73.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.74.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.75.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.76.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.77.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.78.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.79.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.8.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.80.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.81.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.82.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.83.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.84.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.85.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.86.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.87.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.88.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.89.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.9.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.90.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.91.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.92.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.93.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.94.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.95.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.96.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.97.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.98.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.experts.99.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.gate.e_score_correction_bias": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.gate.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.shared_experts.down_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.shared_experts.gate_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00022-of-00048.safetensors",
+ "model.layers.20.mlp.shared_experts.up_proj.weight_scale": "model-00022-of-00048.safetensors",
+ "model.layers.44.mlp.experts.0.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.0.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.0.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.0.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.1.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.1.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.1.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.1.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.10.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.10.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.10.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.10.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.100.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.100.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.100.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.100.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.101.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.101.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.101.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.101.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.102.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.102.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.102.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.102.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.103.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.103.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.103.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.103.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.104.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.104.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.104.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.104.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.105.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.105.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.105.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.105.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.106.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.106.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.106.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.106.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.107.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.107.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.107.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.107.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.108.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.108.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.108.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.108.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.109.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.109.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.109.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.109.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.11.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.11.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.11.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.11.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.110.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.110.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.110.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.110.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.111.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.111.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.111.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.111.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.112.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.112.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.112.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.112.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.113.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.113.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.113.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.113.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.114.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.114.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.114.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.114.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.115.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.115.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.115.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.115.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.116.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.116.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.116.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.116.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.117.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.117.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.117.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.117.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.118.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.118.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.118.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.118.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.119.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.119.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.119.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.119.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.12.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.12.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.12.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.12.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.120.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.120.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.120.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.120.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.121.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.121.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.121.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.121.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.122.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.122.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.122.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.122.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.123.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.123.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.123.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.123.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.124.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.124.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.124.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.124.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.125.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.125.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.125.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.125.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.126.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.126.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.126.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.126.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.127.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.127.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.127.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.127.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.13.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.13.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.13.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.13.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.14.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.14.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.14.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.14.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.15.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.15.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.15.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.15.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.16.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.16.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.16.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.16.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.17.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.17.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.17.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.17.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.18.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.18.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.18.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.18.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.19.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.19.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.19.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.19.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.2.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.2.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.2.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.2.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.20.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.20.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.20.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.20.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.21.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.21.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.21.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.21.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.22.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.22.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.22.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.22.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.23.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.23.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.23.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.23.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.24.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.24.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.24.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.24.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.25.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.25.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.25.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.25.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.26.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.26.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.26.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.26.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.27.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.27.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.27.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.27.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.28.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.28.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.28.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.28.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.29.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.29.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.29.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.29.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.3.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.3.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.3.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.3.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.30.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.30.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.30.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.30.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.31.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.31.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.31.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.31.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.32.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.32.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.32.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.32.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.33.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.33.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.33.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.33.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.34.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.34.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.34.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.34.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.35.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.35.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.35.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.35.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.36.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.36.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.36.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.36.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.37.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.37.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.37.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.37.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.38.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.38.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.38.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.38.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.39.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.39.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.39.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.39.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.4.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.4.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.4.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.4.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.40.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.40.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.40.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.40.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.41.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.41.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.41.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.41.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.42.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.42.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.42.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.42.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.43.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.43.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.43.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.43.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.44.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.44.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.44.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.44.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.45.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.45.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.45.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.45.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.46.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.46.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.46.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.46.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.47.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.47.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.47.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.47.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.48.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.48.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.48.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.48.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.49.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.49.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.49.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.49.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.5.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.5.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.5.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.5.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.50.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.50.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.50.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.50.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.51.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.51.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.51.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.51.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.52.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.52.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.52.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.52.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.53.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.53.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.53.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.53.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.54.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.54.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.54.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.54.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.55.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.55.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.55.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.55.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.56.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.56.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.56.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.56.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.57.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.57.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.57.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.57.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.58.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.58.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.58.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.58.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.59.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.59.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.59.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.59.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.6.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.6.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.6.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.6.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.60.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.60.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.60.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.60.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.61.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.61.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.61.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.61.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.62.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.62.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.62.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.62.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.63.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.63.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.63.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.63.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.64.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.64.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.64.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.64.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.65.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.65.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.65.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.65.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.66.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.66.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.66.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.66.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.67.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.67.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.67.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.67.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.68.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.68.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.68.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.68.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.69.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.69.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.69.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.69.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.7.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.7.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.7.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.7.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.70.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.70.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.70.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.70.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.71.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.71.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.71.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.71.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.72.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.72.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.72.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.72.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.73.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.73.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.73.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.73.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.74.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.74.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.74.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.74.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.75.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.75.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.75.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.75.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.76.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.76.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.76.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.76.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.77.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.77.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.77.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.77.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.78.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.78.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.78.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.78.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.79.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.79.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.79.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.79.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.8.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.8.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.8.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.8.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.80.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.80.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.80.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.80.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.81.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.81.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.81.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.81.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.82.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.82.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.82.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.82.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.83.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.83.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.83.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.83.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.84.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.84.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.84.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.84.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.85.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.85.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.85.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.85.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.86.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.86.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.86.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.86.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.87.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.87.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.87.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.87.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.88.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.88.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.88.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.88.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.89.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.89.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.89.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.89.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.9.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.9.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.9.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.9.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.90.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.90.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.90.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.90.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.91.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.91.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.91.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.91.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.92.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.92.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.92.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.92.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.93.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.93.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.93.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.93.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.94.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.94.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.94.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.94.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.95.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.95.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.95.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.95.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.96.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.96.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.96.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.96.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.97.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.97.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.97.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.97.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.98.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.98.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.98.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.98.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.99.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.99.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.99.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.44.mlp.experts.99.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.0.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.1.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.10.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.100.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.100.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.101.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.101.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.102.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.102.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.103.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.103.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.104.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.104.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.105.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.105.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.106.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.106.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.107.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.107.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.108.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.108.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.109.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.109.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.11.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.110.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.110.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.111.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.111.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.112.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.112.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.113.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.113.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.114.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.114.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.115.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.115.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.116.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.116.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.117.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.117.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.118.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.118.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.119.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.119.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.12.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.120.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.120.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.121.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.121.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.122.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.122.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.123.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.123.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.124.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.124.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.125.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.125.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.126.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.126.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.127.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.127.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.13.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.14.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.15.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.16.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.17.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.18.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.19.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.2.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.20.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.21.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.22.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.23.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.24.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.25.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.26.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.27.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.28.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.29.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.3.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.30.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.31.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.32.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.33.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.34.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.35.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.36.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.37.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.38.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.39.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.4.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.40.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.41.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.42.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.43.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.44.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.45.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.46.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.47.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.48.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.49.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.5.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.50.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.51.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.52.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.53.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.54.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.55.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.56.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.57.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.58.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.59.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.6.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.60.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.61.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.62.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.63.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.64.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.64.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.65.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.65.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.66.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.66.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.67.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.67.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.68.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.68.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.69.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.69.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.7.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.70.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.70.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.71.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.71.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.72.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.72.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.73.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.73.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.74.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.74.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.75.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.75.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.76.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.76.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.77.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.77.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.78.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.78.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.79.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.79.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.8.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.80.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.80.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.81.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.81.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.82.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.82.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.83.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.83.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.84.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.84.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.85.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.85.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.86.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.86.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.87.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.87.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.88.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.88.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.89.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.89.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.9.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.90.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.90.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.91.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.91.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.92.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.92.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.93.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.93.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.94.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.94.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.95.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.95.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.96.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.96.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.97.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.97.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.98.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.98.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.99.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.experts.99.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.gate.e_score_correction_bias": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.gate.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.shared_experts.down_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.shared_experts.gate_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00047-of-00048.safetensors",
+ "model.layers.45.mlp.shared_experts.up_proj.weight_scale": "model-00047-of-00048.safetensors",
+ "model.layers.33.mlp.experts.0.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.0.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.0.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.0.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.1.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.1.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.1.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.1.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.10.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.10.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.10.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.10.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.100.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.100.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.100.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.100.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.101.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.101.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.101.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.101.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.102.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.102.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.102.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.102.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.103.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.103.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.103.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.103.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.104.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.104.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.104.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.104.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.105.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.105.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.105.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.105.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.106.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.106.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.106.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.106.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.107.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.107.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.107.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.107.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.108.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.108.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.108.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.108.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.109.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.109.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.109.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.109.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.11.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.11.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.11.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.11.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.110.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.110.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.110.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.110.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.111.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.111.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.111.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.111.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.112.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.112.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.112.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.112.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.113.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.113.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.113.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.113.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.114.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.114.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.114.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.114.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.115.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.115.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.115.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.115.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.116.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.116.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.116.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.116.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.117.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.117.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.117.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.117.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.118.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.118.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.118.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.118.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.119.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.119.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.119.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.119.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.12.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.12.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.12.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.12.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.120.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.120.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.120.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.120.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.121.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.121.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.121.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.121.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.122.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.122.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.122.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.122.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.123.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.123.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.123.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.123.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.124.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.124.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.124.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.124.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.125.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.125.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.125.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.125.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.126.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.126.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.126.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.126.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.127.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.127.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.127.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.127.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.13.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.13.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.13.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.13.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.14.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.14.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.14.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.14.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.15.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.15.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.15.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.15.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.16.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.16.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.16.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.16.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.17.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.17.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.17.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.17.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.18.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.18.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.18.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.18.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.19.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.19.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.19.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.19.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.2.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.2.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.2.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.2.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.20.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.20.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.20.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.20.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.21.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.21.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.21.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.21.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.22.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.22.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.22.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.22.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.23.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.23.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.23.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.23.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.24.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.24.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.24.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.24.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.25.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.25.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.25.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.25.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.26.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.26.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.26.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.26.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.27.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.27.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.27.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.27.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.28.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.28.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.28.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.28.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.29.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.29.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.29.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.29.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.3.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.3.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.3.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.3.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.30.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.30.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.30.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.30.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.31.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.31.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.31.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.31.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.32.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.32.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.32.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.32.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.33.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.33.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.33.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.33.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.34.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.34.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.34.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.34.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.35.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.35.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.35.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.35.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.36.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.36.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.36.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.36.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.37.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.37.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.37.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.37.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.38.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.38.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.38.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.38.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.39.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.39.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.39.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.39.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.4.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.4.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.4.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.4.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.40.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.40.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.40.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.40.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.41.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.41.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.41.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.41.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.42.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.42.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.42.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.42.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.43.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.43.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.43.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.43.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.44.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.44.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.44.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.44.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.45.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.45.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.45.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.45.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.46.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.46.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.46.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.46.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.47.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.47.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.47.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.47.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.48.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.48.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.48.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.48.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.49.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.49.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.49.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.49.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.5.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.5.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.5.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.5.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.50.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.50.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.50.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.50.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.51.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.51.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.51.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.51.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.52.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.52.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.52.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.52.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.53.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.53.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.53.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.53.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.54.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.54.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.54.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.54.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.55.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.55.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.55.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.55.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.56.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.56.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.56.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.56.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.57.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.57.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.57.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.57.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.58.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.58.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.58.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.58.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.59.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.59.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.59.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.59.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.6.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.6.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.6.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.6.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.60.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.60.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.60.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.60.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.61.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.61.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.61.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.61.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.62.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.62.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.62.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.62.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.63.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.63.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.63.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.63.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.64.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.64.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.64.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.64.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.65.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.65.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.65.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.65.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.66.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.66.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.66.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.66.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.67.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.67.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.67.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.67.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.68.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.68.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.68.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.68.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.69.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.69.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.69.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.69.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.7.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.7.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.7.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.7.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.70.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.70.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.70.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.70.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.71.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.71.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.71.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.71.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.72.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.72.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.72.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.72.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.73.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.73.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.73.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.73.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.74.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.74.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.74.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.74.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.75.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.75.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.75.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.75.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.76.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.76.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.76.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.76.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.77.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.77.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.77.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.77.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.78.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.78.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.78.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.78.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.79.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.79.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.79.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.79.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.8.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.8.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.8.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.8.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.80.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.80.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.80.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.80.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.81.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.81.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.81.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.81.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.82.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.82.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.82.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.82.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.83.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.83.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.83.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.83.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.84.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.84.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.84.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.84.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.85.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.85.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.85.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.85.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.86.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.86.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.86.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.86.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.87.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.87.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.87.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.87.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.88.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.88.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.88.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.88.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.89.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.89.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.89.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.89.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.9.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.9.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.9.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.9.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.90.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.90.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.90.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.90.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.91.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.91.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.91.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.91.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.92.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.92.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.92.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.92.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.93.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.93.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.93.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.93.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.94.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.94.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.94.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.94.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.95.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.95.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.95.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.95.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.96.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.96.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.96.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.96.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.97.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.97.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.97.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.97.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.98.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.98.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.98.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.98.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.99.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.99.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.99.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.33.mlp.experts.99.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.0.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.1.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.10.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.100.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.100.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.101.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.101.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.102.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.102.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.103.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.103.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.104.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.104.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.105.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.105.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.106.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.106.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.107.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.107.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.108.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.108.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.109.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.109.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.11.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.110.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.110.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.111.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.111.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.112.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.112.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.113.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.113.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.114.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.114.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.115.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.115.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.116.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.116.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.117.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.117.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.118.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.118.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.119.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.119.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.12.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.120.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.120.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.121.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.121.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.122.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.122.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.123.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.123.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.124.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.124.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.125.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.125.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.126.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.126.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.127.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.127.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.13.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.14.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.15.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.16.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.17.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.18.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.19.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.2.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.20.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.21.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.22.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.23.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.24.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.25.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.26.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.27.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.28.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.29.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.3.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.30.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.31.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.32.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.33.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.34.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.35.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.36.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.37.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.38.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.39.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.4.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.40.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.41.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.42.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.43.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.44.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.45.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.46.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.47.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.48.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.49.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.5.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.50.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.51.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.52.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.53.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.54.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.55.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.56.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.57.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.58.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.59.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.6.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.60.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.61.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.62.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.63.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.64.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.64.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.65.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.65.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.66.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.66.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.67.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.67.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.68.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.68.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.69.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.69.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.7.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.70.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.70.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.71.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.71.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.72.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.72.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.73.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.73.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.74.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.74.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.75.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.75.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.76.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.76.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.77.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.77.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.78.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.78.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.79.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.79.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.8.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.80.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.80.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.81.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.81.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.82.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.82.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.83.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.83.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.84.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.84.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.85.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.85.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.86.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.86.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.87.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.87.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.88.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.88.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.89.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.89.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.9.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.90.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.90.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.91.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.91.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.92.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.92.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.93.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.93.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.94.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.94.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.95.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.95.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.96.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.96.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.97.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.97.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.98.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.98.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.99.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.experts.99.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.gate.e_score_correction_bias": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.gate.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.shared_experts.down_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.shared_experts.gate_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00036-of-00048.safetensors",
+ "model.layers.34.mlp.shared_experts.up_proj.weight_scale": "model-00036-of-00048.safetensors",
+ "model.layers.45.mlp.experts.0.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.0.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.0.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.0.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.1.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.1.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.1.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.1.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.10.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.10.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.10.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.10.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.100.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.100.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.100.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.100.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.101.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.101.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.101.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.101.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.102.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.102.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.102.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.102.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.103.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.103.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.103.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.103.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.104.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.104.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.104.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.104.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.105.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.105.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.105.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.105.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.106.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.106.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.106.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.106.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.107.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.107.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.107.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.107.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.108.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.108.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.108.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.108.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.109.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.109.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.109.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.109.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.11.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.11.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.11.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.11.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.110.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.110.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.110.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.110.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.111.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.111.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.111.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.111.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.112.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.112.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.112.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.112.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.113.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.113.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.113.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.113.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.114.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.114.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.114.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.114.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.115.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.115.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.115.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.115.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.116.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.116.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.116.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.116.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.117.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.117.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.117.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.117.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.118.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.118.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.118.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.118.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.119.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.119.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.119.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.119.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.12.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.12.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.12.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.12.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.120.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.120.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.120.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.120.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.121.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.121.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.121.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.121.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.122.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.122.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.122.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.122.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.123.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.123.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.123.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.123.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.124.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.124.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.124.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.124.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.125.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.125.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.125.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.125.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.126.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.126.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.126.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.126.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.127.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.127.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.127.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.127.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.13.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.13.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.13.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.13.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.14.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.14.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.14.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.14.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.15.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.15.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.15.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.15.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.16.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.16.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.16.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.16.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.17.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.17.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.17.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.17.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.18.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.18.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.18.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.18.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.19.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.19.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.19.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.19.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.2.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.2.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.2.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.2.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.20.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.20.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.20.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.20.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.21.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.21.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.21.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.21.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.22.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.22.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.22.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.22.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.23.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.23.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.23.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.23.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.24.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.24.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.24.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.24.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.25.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.25.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.25.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.25.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.26.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.26.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.26.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.26.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.27.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.27.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.27.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.27.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.28.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.28.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.28.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.28.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.29.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.29.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.29.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.29.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.3.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.3.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.3.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.3.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.30.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.30.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.30.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.30.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.31.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.31.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.31.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.31.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.32.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.32.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.32.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.32.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.33.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.33.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.33.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.33.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.34.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.34.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.34.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.34.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.35.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.35.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.35.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.35.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.36.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.36.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.36.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.36.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.37.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.37.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.37.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.37.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.38.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.38.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.38.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.38.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.39.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.39.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.39.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.39.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.4.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.4.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.4.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.4.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.40.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.40.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.40.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.40.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.41.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.41.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.41.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.41.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.42.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.42.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.42.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.42.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.43.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.43.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.43.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.43.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.44.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.44.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.44.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.44.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.45.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.45.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.45.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.45.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.46.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.46.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.46.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.46.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.47.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.47.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.47.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.47.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.48.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.48.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.48.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.48.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.49.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.49.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.49.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.49.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.5.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.5.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.5.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.5.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.50.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.50.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.50.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.50.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.51.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.51.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.51.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.51.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.52.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.52.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.52.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.52.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.53.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.53.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.53.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.53.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.54.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.54.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.54.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.54.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.55.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.55.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.55.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.55.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.56.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.56.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.56.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.56.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.57.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.57.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.57.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.57.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.58.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.58.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.58.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.58.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.59.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.59.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.59.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.59.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.6.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.6.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.6.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.6.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.60.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.60.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.60.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.60.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.61.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.61.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.61.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.61.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.62.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.62.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.62.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.62.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.63.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.63.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.63.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.63.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.64.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.64.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.64.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.64.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.65.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.65.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.65.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.65.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.66.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.66.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.66.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.66.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.67.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.67.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.67.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.67.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.68.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.68.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.68.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.68.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.69.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.69.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.69.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.69.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.7.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.7.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.7.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.7.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.70.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.70.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.70.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.70.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.71.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.71.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.71.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.71.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.72.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.72.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.72.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.72.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.73.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.73.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.73.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.73.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.74.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.74.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.74.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.74.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.75.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.75.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.75.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.75.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.76.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.76.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.76.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.76.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.77.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.77.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.77.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.77.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.78.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.78.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.78.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.78.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.79.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.79.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.79.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.79.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.8.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.8.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.8.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.8.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.80.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.80.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.80.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.80.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.81.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.81.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.81.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.81.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.82.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.82.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.82.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.82.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.83.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.83.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.83.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.83.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.84.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.84.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.84.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.84.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.85.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.85.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.85.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.85.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.86.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.86.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.86.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.86.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.87.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.87.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.87.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.87.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.88.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.88.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.88.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.88.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.89.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.89.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.89.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.89.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.9.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.9.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.9.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.9.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.90.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.90.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.90.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.90.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.91.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.91.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.91.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.91.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.92.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.92.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.92.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.92.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.93.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.93.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.93.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.93.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.94.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.94.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.94.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.94.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.95.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.95.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.95.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.95.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.96.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.96.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.96.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.96.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.97.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.97.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.97.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.97.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.98.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.98.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.98.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.98.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.99.down_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.99.down_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.99.up_proj.weight": "model-00048-of-00048.safetensors",
+ "model.layers.45.mlp.experts.99.up_proj.weight_scale": "model-00048-of-00048.safetensors",
+ "model.layers.29.mlp.experts.0.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.0.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.0.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.0.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.1.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.1.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.1.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.1.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.10.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.10.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.10.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.10.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.100.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.100.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.100.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.100.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.101.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.101.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.101.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.101.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.102.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.102.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.102.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.102.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.103.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.103.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.103.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.103.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.104.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.104.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.104.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.104.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.105.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.105.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.105.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.105.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.106.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.106.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.106.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.106.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.107.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.107.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.107.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.107.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.108.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.108.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.108.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.108.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.109.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.109.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.109.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.109.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.11.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.11.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.11.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.11.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.110.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.110.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.110.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.110.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.111.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.111.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.111.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.111.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.112.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.112.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.112.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.112.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.113.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.113.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.113.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.113.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.114.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.114.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.114.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.114.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.115.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.115.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.115.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.115.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.116.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.116.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.116.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.116.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.117.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.117.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.117.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.117.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.118.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.118.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.118.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.118.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.119.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.119.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.119.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.119.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.12.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.12.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.12.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.12.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.120.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.120.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.120.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.120.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.121.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.121.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.121.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.121.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.122.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.122.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.122.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.122.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.123.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.123.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.123.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.123.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.124.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.124.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.124.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.124.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.125.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.125.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.125.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.125.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.126.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.126.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.126.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.126.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.127.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.127.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.127.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.127.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.13.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.13.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.13.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.13.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.14.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.14.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.14.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.14.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.15.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.15.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.15.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.15.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.16.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.16.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.16.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.16.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.17.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.17.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.17.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.17.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.18.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.18.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.18.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.18.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.19.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.19.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.19.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.19.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.2.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.2.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.2.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.2.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.20.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.20.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.20.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.20.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.21.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.21.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.21.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.21.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.22.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.22.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.22.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.22.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.23.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.23.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.23.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.23.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.24.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.24.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.24.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.24.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.25.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.25.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.25.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.25.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.26.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.26.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.26.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.26.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.27.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.27.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.27.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.27.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.28.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.28.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.28.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.28.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.29.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.29.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.29.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.29.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.3.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.3.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.3.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.3.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.30.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.30.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.30.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.30.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.31.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.31.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.31.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.31.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.32.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.32.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.32.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.32.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.33.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.33.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.33.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.33.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.34.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.34.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.34.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.34.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.35.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.35.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.35.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.35.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.36.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.36.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.36.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.36.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.37.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.37.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.37.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.37.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.38.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.38.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.38.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.38.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.39.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.39.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.39.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.39.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.4.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.4.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.4.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.4.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.40.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.40.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.40.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.40.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.41.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.41.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.41.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.41.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.42.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.42.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.42.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.42.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.43.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.43.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.43.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.43.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.44.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.44.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.44.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.44.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.45.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.45.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.45.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.45.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.46.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.46.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.46.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.46.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.47.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.47.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.47.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.47.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.48.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.48.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.48.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.48.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.49.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.49.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.49.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.49.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.5.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.5.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.5.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.5.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.50.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.50.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.50.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.50.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.51.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.51.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.51.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.51.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.52.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.52.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.52.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.52.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.53.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.53.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.53.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.53.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.54.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.54.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.54.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.54.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.55.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.55.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.55.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.55.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.56.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.56.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.56.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.56.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.57.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.57.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.57.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.57.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.58.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.58.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.58.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.58.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.59.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.59.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.59.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.59.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.6.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.6.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.6.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.6.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.60.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.60.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.60.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.60.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.61.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.61.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.61.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.61.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.62.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.62.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.62.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.62.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.63.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.63.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.63.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.63.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.64.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.64.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.64.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.64.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.65.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.65.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.65.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.65.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.66.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.66.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.66.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.66.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.67.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.67.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.67.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.67.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.68.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.68.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.68.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.68.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.69.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.69.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.69.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.69.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.7.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.7.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.7.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.7.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.70.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.70.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.70.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.70.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.71.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.71.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.71.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.71.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.72.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.72.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.72.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.72.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.73.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.73.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.73.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.73.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.74.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.74.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.74.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.74.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.75.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.75.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.75.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.75.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.76.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.76.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.76.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.76.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.77.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.77.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.77.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.77.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.78.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.78.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.78.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.78.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.79.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.79.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.79.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.79.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.8.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.8.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.8.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.8.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.80.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.80.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.80.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.80.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.81.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.81.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.81.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.81.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.82.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.82.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.82.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.82.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.83.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.83.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.83.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.83.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.84.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.84.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.84.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.84.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.85.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.85.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.85.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.85.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.86.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.86.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.86.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.86.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.87.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.87.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.87.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.87.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.88.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.88.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.88.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.88.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.89.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.89.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.89.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.89.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.9.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.9.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.9.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.9.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.90.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.90.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.90.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.90.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.91.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.91.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.91.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.91.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.92.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.92.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.92.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.92.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.93.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.93.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.93.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.93.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.94.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.94.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.94.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.94.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.95.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.95.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.95.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.95.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.96.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.96.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.96.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.96.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.97.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.97.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.97.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.97.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.98.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.98.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.98.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.98.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.99.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.99.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.99.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.29.mlp.experts.99.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.0.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.1.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.10.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.100.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.101.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.102.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.103.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.104.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.105.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.106.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.107.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.108.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.109.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.11.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.110.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.111.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.112.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.113.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.114.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.115.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.116.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.117.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.118.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.119.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.12.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.120.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.121.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.122.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.123.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.124.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.125.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.126.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.127.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.13.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.14.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.15.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.16.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.17.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.18.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.19.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.2.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.20.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.21.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.22.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.23.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.24.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.25.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.26.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.27.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.28.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.29.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.3.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.30.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.31.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.32.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.33.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.34.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.35.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.36.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.37.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.38.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.39.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.4.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.40.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.41.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.42.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.43.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.44.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.45.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.46.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.47.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.48.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.49.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.5.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.50.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.51.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.52.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.53.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.54.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.55.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.56.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.57.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.58.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.59.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.6.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.60.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.61.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.62.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.63.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.64.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.65.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.66.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.67.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.68.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.69.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.7.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.70.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.71.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.72.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.73.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.74.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.75.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.76.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.77.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.78.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.79.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.8.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.80.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.81.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.82.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.83.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.84.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.85.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.86.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.87.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.88.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.89.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.9.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.90.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.91.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.92.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.93.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.94.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.95.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.96.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.97.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.98.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.experts.99.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.gate.e_score_correction_bias": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.gate.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.shared_experts.down_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.shared_experts.gate_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00032-of-00048.safetensors",
+ "model.layers.30.mlp.shared_experts.up_proj.weight_scale": "model-00032-of-00048.safetensors",
+ "model.layers.13.mlp.experts.0.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.0.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.0.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.0.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.1.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.1.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.1.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.1.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.10.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.10.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.10.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.10.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.100.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.100.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.100.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.100.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.101.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.101.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.101.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.101.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.102.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.102.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.102.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.102.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.103.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.103.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.103.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.103.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.104.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.104.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.104.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.104.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.105.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.105.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.105.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.105.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.106.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.106.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.106.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.106.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.107.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.107.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.107.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.107.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.108.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.108.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.108.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.108.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.109.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.109.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.109.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.109.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.11.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.11.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.11.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.11.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.110.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.110.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.110.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.110.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.111.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.111.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.111.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.111.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.112.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.112.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.112.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.112.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.113.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.113.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.113.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.113.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.114.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.114.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.114.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.114.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.115.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.115.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.115.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.115.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.116.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.116.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.116.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.116.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.117.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.117.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.117.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.117.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.118.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.118.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.118.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.118.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.119.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.119.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.119.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.119.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.12.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.12.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.12.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.12.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.120.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.120.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.120.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.120.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.121.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.121.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.121.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.121.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.122.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.122.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.122.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.122.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.123.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.123.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.123.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.123.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.124.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.124.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.124.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.124.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.125.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.125.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.125.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.125.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.126.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.126.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.126.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.126.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.127.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.127.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.127.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.127.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.13.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.13.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.13.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.13.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.14.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.14.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.14.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.14.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.15.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.15.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.15.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.15.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.16.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.16.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.16.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.16.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.17.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.17.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.17.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.17.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.18.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.18.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.18.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.18.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.19.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.19.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.19.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.19.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.2.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.2.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.2.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.2.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.20.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.20.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.20.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.20.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.21.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.21.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.21.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.21.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.22.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.22.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.22.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.22.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.23.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.23.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.23.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.23.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.24.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.24.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.24.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.24.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.25.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.25.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.25.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.25.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.26.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.26.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.26.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.26.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.27.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.27.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.27.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.27.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.28.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.28.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.28.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.28.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.29.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.29.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.29.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.29.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.3.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.3.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.3.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.3.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.30.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.30.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.30.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.30.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.31.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.31.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.31.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.31.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.32.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.32.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.32.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.32.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.33.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.33.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.33.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.33.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.34.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.34.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.34.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.34.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.35.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.35.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.35.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.35.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.36.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.36.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.36.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.36.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.37.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.37.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.37.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.37.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.38.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.38.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.38.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.38.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.39.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.39.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.39.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.39.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.4.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.4.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.4.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.4.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.40.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.40.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.40.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.40.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.41.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.41.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.41.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.41.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.42.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.42.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.42.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.42.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.43.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.43.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.43.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.43.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.44.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.44.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.44.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.44.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.45.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.45.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.45.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.45.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.46.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.46.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.46.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.46.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.47.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.47.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.47.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.47.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.48.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.48.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.48.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.48.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.49.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.49.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.49.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.49.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.5.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.5.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.5.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.5.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.50.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.50.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.50.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.50.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.51.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.51.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.51.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.51.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.52.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.52.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.52.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.52.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.53.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.53.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.53.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.53.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.54.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.54.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.54.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.54.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.55.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.55.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.55.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.55.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.56.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.56.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.56.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.56.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.57.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.57.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.57.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.57.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.58.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.58.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.58.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.58.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.59.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.59.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.59.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.59.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.6.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.6.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.6.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.6.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.60.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.60.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.60.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.60.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.61.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.61.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.61.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.61.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.62.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.62.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.62.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.62.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.63.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.63.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.63.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.63.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.64.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.64.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.64.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.64.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.65.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.65.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.65.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.65.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.66.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.66.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.66.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.66.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.67.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.67.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.67.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.67.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.68.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.68.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.68.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.68.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.69.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.69.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.69.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.69.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.7.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.7.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.7.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.7.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.70.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.70.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.70.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.70.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.71.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.71.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.71.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.71.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.72.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.72.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.72.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.72.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.73.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.73.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.73.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.73.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.74.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.74.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.74.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.74.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.75.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.75.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.75.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.75.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.76.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.76.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.76.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.76.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.77.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.77.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.77.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.77.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.78.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.78.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.78.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.78.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.79.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.79.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.79.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.79.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.8.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.8.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.8.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.8.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.80.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.80.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.80.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.80.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.81.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.81.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.81.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.81.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.82.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.82.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.82.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.82.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.83.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.83.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.83.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.83.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.84.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.84.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.84.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.84.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.85.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.85.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.85.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.85.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.86.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.86.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.86.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.86.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.87.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.87.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.87.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.87.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.88.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.88.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.88.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.88.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.89.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.89.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.89.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.89.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.9.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.9.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.9.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.9.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.90.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.90.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.90.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.90.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.91.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.91.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.91.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.91.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.92.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.92.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.92.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.92.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.93.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.93.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.93.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.93.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.94.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.94.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.94.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.94.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.95.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.95.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.95.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.95.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.96.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.96.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.96.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.96.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.97.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.97.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.97.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.97.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.98.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.98.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.98.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.98.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.99.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.99.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.99.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.13.mlp.experts.99.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.0.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.1.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.10.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.100.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.101.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.102.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.103.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.104.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.105.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.106.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.107.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.108.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.109.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.11.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.110.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.111.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.112.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.113.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.114.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.115.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.116.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.117.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.118.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.119.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.12.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.120.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.121.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.122.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.123.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.124.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.125.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.126.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.127.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.13.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.14.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.15.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.16.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.17.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.18.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.19.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.2.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.20.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.21.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.22.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.23.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.24.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.25.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.26.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.27.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.28.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.29.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.3.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.30.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.31.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.32.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.33.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.34.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.35.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.36.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.37.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.38.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.39.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.4.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.40.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.41.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.42.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.43.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.44.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.45.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.46.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.47.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.48.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.49.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.5.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.50.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.51.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.52.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.53.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.54.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.55.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.56.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.57.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.58.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.59.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.6.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.60.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.61.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.62.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.63.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.64.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.65.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.66.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.67.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.68.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.69.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.7.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.70.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.71.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.72.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.73.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.74.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.75.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.76.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.77.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.78.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.79.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.8.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.80.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.81.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.82.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.83.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.84.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.85.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.86.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.87.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.88.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.89.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.9.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.90.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.91.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.92.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.93.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.94.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.95.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.96.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.97.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.98.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.experts.99.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.gate.e_score_correction_bias": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.gate.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.shared_experts.down_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.shared_experts.gate_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00016-of-00048.safetensors",
+ "model.layers.14.mlp.shared_experts.up_proj.weight_scale": "model-00016-of-00048.safetensors",
+ "model.layers.30.mlp.experts.0.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.0.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.0.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.0.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.1.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.1.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.1.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.1.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.10.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.10.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.10.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.10.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.100.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.100.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.100.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.100.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.101.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.101.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.101.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.101.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.102.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.102.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.102.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.102.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.103.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.103.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.103.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.103.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.104.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.104.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.104.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.104.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.105.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.105.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.105.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.105.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.106.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.106.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.106.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.106.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.107.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.107.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.107.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.107.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.108.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.108.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.108.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.108.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.109.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.109.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.109.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.109.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.11.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.11.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.11.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.11.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.110.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.110.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.110.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.110.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.111.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.111.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.111.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.111.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.112.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.112.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.112.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.112.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.113.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.113.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.113.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.113.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.114.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.114.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.114.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.114.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.115.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.115.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.115.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.115.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.116.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.116.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.116.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.116.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.117.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.117.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.117.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.117.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.118.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.118.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.118.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.118.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.119.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.119.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.119.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.119.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.12.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.12.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.12.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.12.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.120.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.120.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.120.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.120.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.121.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.121.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.121.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.121.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.122.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.122.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.122.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.122.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.123.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.123.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.123.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.123.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.124.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.124.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.124.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.124.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.125.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.125.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.125.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.125.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.126.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.126.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.126.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.126.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.127.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.127.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.127.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.127.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.13.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.13.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.13.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.13.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.14.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.14.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.14.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.14.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.15.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.15.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.15.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.15.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.16.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.16.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.16.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.16.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.17.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.17.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.17.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.17.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.18.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.18.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.18.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.18.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.19.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.19.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.19.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.19.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.2.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.2.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.2.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.2.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.20.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.20.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.20.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.20.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.21.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.21.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.21.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.21.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.22.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.22.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.22.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.22.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.23.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.23.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.23.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.23.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.24.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.24.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.24.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.24.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.25.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.25.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.25.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.25.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.26.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.26.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.26.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.26.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.27.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.27.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.27.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.27.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.28.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.28.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.28.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.28.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.29.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.29.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.29.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.29.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.3.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.3.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.3.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.3.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.30.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.30.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.30.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.30.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.31.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.31.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.31.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.31.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.32.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.32.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.32.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.32.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.33.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.33.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.33.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.33.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.34.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.34.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.34.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.34.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.35.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.35.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.35.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.35.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.36.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.36.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.36.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.36.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.37.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.37.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.37.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.37.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.38.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.38.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.38.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.38.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.39.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.39.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.39.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.39.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.4.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.4.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.4.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.4.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.40.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.40.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.40.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.40.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.41.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.41.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.41.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.41.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.42.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.42.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.42.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.42.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.43.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.43.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.43.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.43.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.44.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.44.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.44.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.44.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.45.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.45.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.45.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.45.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.46.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.46.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.46.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.46.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.47.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.47.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.47.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.47.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.48.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.48.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.48.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.48.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.49.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.49.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.49.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.49.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.5.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.5.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.5.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.5.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.50.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.50.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.50.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.50.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.51.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.51.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.51.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.51.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.52.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.52.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.52.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.52.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.53.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.53.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.53.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.53.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.54.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.54.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.54.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.54.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.55.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.55.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.55.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.55.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.56.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.56.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.56.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.56.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.57.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.57.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.57.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.57.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.58.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.58.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.58.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.58.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.59.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.59.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.59.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.59.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.6.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.6.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.6.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.6.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.60.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.60.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.60.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.60.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.61.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.61.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.61.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.61.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.62.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.62.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.62.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.62.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.63.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.63.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.63.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.63.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.64.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.64.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.64.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.64.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.65.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.65.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.65.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.65.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.66.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.66.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.66.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.66.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.67.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.67.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.67.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.67.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.68.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.68.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.68.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.68.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.69.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.69.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.69.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.69.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.7.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.7.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.7.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.7.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.70.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.70.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.70.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.70.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.71.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.71.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.71.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.71.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.72.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.72.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.72.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.72.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.73.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.73.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.73.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.73.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.74.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.74.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.74.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.74.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.75.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.75.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.75.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.75.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.76.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.76.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.76.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.76.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.77.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.77.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.77.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.77.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.78.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.78.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.78.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.78.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.79.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.79.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.79.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.79.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.8.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.8.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.8.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.8.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.80.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.80.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.80.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.80.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.81.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.81.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.81.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.81.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.82.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.82.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.82.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.82.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.83.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.83.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.83.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.83.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.84.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.84.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.84.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.84.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.85.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.85.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.85.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.85.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.86.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.86.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.86.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.86.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.87.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.87.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.87.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.87.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.88.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.88.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.88.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.88.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.89.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.89.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.89.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.89.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.9.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.9.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.9.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.9.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.90.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.90.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.90.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.90.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.91.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.91.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.91.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.91.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.92.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.92.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.92.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.92.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.93.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.93.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.93.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.93.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.94.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.94.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.94.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.94.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.95.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.95.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.95.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.95.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.96.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.96.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.96.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.96.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.97.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.97.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.97.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.97.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.98.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.98.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.98.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.98.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.99.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.99.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.99.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.30.mlp.experts.99.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.0.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.1.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.10.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.100.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.101.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.102.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.103.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.104.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.105.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.106.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.107.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.108.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.109.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.11.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.110.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.111.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.112.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.113.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.114.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.115.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.116.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.117.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.118.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.119.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.12.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.120.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.121.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.122.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.123.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.124.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.125.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.126.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.127.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.13.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.14.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.15.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.16.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.17.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.18.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.19.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.2.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.20.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.21.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.22.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.23.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.24.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.25.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.26.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.27.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.28.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.29.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.3.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.30.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.31.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.32.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.33.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.34.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.35.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.36.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.37.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.38.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.39.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.4.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.40.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.41.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.42.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.43.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.44.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.45.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.46.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.47.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.48.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.49.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.5.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.50.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.51.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.52.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.53.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.54.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.55.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.56.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.57.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.58.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.59.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.6.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.60.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.61.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.62.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.63.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.64.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.65.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.66.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.67.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.68.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.69.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.7.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.70.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.71.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.72.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.73.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.74.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.75.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.76.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.77.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.78.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.79.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.8.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.80.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.81.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.82.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.83.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.84.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.85.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.86.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.87.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.88.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.89.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.9.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.90.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.91.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.92.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.93.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.94.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.95.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.96.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.97.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.98.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.experts.99.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.gate.e_score_correction_bias": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.gate.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.shared_experts.down_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.shared_experts.gate_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00033-of-00048.safetensors",
+ "model.layers.31.mlp.shared_experts.up_proj.weight_scale": "model-00033-of-00048.safetensors",
+ "lm_head.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.0.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.1.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.10.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.100.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.100.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.101.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.101.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.102.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.102.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.103.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.103.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.104.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.104.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.105.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.105.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.106.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.106.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.107.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.107.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.108.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.108.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.109.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.109.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.11.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.110.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.110.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.111.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.111.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.112.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.112.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.113.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.113.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.114.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.114.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.115.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.115.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.116.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.116.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.117.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.117.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.118.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.118.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.119.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.119.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.12.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.120.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.120.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.121.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.121.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.122.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.122.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.123.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.123.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.124.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.124.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.125.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.125.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.126.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.126.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.127.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.127.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.13.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.14.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.15.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.16.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.17.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.18.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.19.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.2.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.20.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.21.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.22.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.23.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.24.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.25.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.26.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.27.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.28.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.29.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.3.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.30.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.31.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.32.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.33.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.34.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.35.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.36.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.37.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.38.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.39.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.4.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.40.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.41.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.42.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.43.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.44.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.45.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.46.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.47.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.48.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.49.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.5.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.50.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.51.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.52.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.53.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.54.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.55.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.56.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.57.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.58.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.59.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.6.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.60.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.61.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.62.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.63.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.64.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.64.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.65.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.65.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.66.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.66.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.67.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.67.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.68.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.68.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.69.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.69.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.7.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.70.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.70.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.71.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.71.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.72.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.72.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.73.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.73.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.74.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.74.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.75.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.75.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.76.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.76.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.77.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.77.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.78.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.78.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.79.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.79.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.8.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.80.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.80.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.81.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.81.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.82.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.82.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.83.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.83.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.84.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.84.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.85.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.85.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.86.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.86.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.87.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.87.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.88.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.88.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.89.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.89.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.9.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.90.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.90.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.91.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.91.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.92.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.92.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.93.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.93.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.94.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.94.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.95.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.95.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.96.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.96.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.97.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.97.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.98.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.98.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.99.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.experts.99.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.gate.e_score_correction_bias": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.gate.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.shared_experts.down_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.shared_experts.gate_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.1.mlp.shared_experts.up_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.38.self_attn.k_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.38.self_attn.o_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.38.self_attn.q_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.38.self_attn.v_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.39.self_attn.k_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.39.self_attn.o_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.39.self_attn.q_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.39.self_attn.v_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.40.input_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.40.self_attn.k_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.40.self_attn.o_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.40.self_attn.q_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.40.self_attn.v_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.41.input_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.41.self_attn.k_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.41.self_attn.o_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.41.self_attn.q_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.41.self_attn.v_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.42.input_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.42.self_attn.k_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.42.self_attn.o_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.42.self_attn.q_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.42.self_attn.v_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.43.input_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.43.self_attn.k_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.43.self_attn.o_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.43.self_attn.q_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.43.self_attn.v_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.44.input_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.44.self_attn.k_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.44.self_attn.o_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.44.self_attn.q_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.44.self_attn.v_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.45.input_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.45.self_attn.k_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.45.self_attn.o_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.45.self_attn.q_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00048.safetensors",
+ "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00048.safetensors",
+ "model.layers.45.self_attn.v_proj.weight_scale": "model-00003-of-00048.safetensors",
+ "model.norm.weight": "model-00003-of-00048.safetensors",
+ "model.layers.42.mlp.experts.0.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.0.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.0.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.0.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.1.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.1.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.1.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.1.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.10.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.10.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.10.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.10.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.100.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.100.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.100.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.100.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.101.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.101.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.101.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.101.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.102.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.102.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.102.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.102.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.103.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.103.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.103.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.103.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.104.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.104.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.104.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.104.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.105.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.105.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.105.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.105.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.106.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.106.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.106.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.106.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.107.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.107.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.107.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.107.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.108.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.108.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.108.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.108.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.109.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.109.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.109.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.109.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.11.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.11.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.11.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.11.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.110.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.110.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.110.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.110.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.111.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.111.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.111.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.111.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.112.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.112.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.112.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.112.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.113.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.113.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.113.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.113.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.114.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.114.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.114.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.114.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.115.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.115.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.115.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.115.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.116.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.116.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.116.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.116.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.117.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.117.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.117.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.117.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.118.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.118.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.118.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.118.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.119.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.119.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.119.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.119.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.12.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.12.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.12.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.12.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.120.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.120.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.120.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.120.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.121.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.121.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.121.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.121.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.122.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.122.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.122.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.122.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.123.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.123.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.123.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.123.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.124.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.124.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.124.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.124.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.125.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.125.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.125.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.125.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.126.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.126.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.126.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.126.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.127.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.127.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.127.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.127.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.13.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.13.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.13.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.13.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.14.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.14.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.14.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.14.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.15.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.15.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.15.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.15.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.16.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.16.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.16.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.16.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.17.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.17.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.17.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.17.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.18.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.18.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.18.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.18.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.19.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.19.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.19.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.19.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.2.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.2.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.2.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.2.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.20.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.20.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.20.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.20.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.21.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.21.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.21.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.21.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.22.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.22.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.22.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.22.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.23.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.23.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.23.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.23.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.24.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.24.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.24.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.24.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.25.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.25.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.25.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.25.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.26.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.26.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.26.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.26.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.27.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.27.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.27.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.27.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.28.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.28.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.28.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.28.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.29.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.29.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.29.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.29.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.3.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.3.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.3.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.3.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.30.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.30.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.30.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.30.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.31.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.31.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.31.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.31.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.32.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.32.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.32.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.32.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.33.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.33.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.33.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.33.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.34.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.34.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.34.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.34.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.35.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.35.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.35.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.35.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.36.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.36.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.36.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.36.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.37.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.37.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.37.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.37.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.38.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.38.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.38.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.38.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.39.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.39.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.39.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.39.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.4.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.4.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.4.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.4.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.40.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.40.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.40.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.40.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.41.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.41.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.41.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.41.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.42.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.42.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.42.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.42.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.43.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.43.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.43.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.43.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.44.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.44.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.44.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.44.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.45.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.45.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.45.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.45.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.46.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.46.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.46.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.46.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.47.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.47.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.47.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.47.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.48.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.48.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.48.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.48.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.49.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.49.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.49.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.49.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.5.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.5.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.5.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.5.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.50.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.50.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.50.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.50.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.51.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.51.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.51.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.51.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.52.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.52.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.52.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.52.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.53.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.53.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.53.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.53.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.54.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.54.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.54.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.54.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.55.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.55.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.55.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.55.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.56.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.56.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.56.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.56.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.57.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.57.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.57.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.57.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.58.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.58.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.58.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.58.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.59.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.59.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.59.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.59.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.6.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.6.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.6.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.6.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.60.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.60.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.60.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.60.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.61.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.61.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.61.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.61.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.62.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.62.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.62.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.62.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.63.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.63.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.63.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.63.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.64.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.64.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.64.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.64.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.65.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.65.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.65.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.65.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.66.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.66.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.66.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.66.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.67.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.67.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.67.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.67.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.68.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.68.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.68.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.68.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.69.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.69.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.69.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.69.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.7.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.7.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.7.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.7.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.70.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.70.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.70.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.70.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.71.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.71.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.71.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.71.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.72.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.72.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.72.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.72.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.73.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.73.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.73.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.73.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.74.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.74.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.74.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.74.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.75.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.75.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.75.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.75.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.76.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.76.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.76.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.76.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.77.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.77.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.77.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.77.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.78.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.78.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.78.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.78.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.79.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.79.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.79.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.79.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.8.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.8.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.8.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.8.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.80.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.80.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.80.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.80.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.81.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.81.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.81.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.81.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.82.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.82.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.82.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.82.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.83.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.83.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.83.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.83.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.84.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.84.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.84.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.84.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.85.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.85.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.85.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.85.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.86.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.86.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.86.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.86.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.87.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.87.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.87.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.87.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.88.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.88.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.88.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.88.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.89.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.89.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.89.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.89.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.9.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.9.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.9.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.9.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.90.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.90.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.90.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.90.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.91.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.91.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.91.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.91.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.92.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.92.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.92.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.92.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.93.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.93.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.93.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.93.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.94.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.94.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.94.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.94.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.95.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.95.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.95.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.95.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.96.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.96.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.96.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.96.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.97.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.97.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.97.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.97.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.98.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.98.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.98.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.98.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.99.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.99.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.99.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.42.mlp.experts.99.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.0.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.1.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.10.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.100.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.100.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.101.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.101.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.102.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.102.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.103.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.103.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.104.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.104.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.105.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.105.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.106.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.106.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.107.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.107.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.108.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.108.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.109.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.109.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.11.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.110.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.110.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.111.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.111.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.112.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.112.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.113.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.113.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.114.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.114.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.115.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.115.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.116.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.116.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.117.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.117.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.118.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.118.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.119.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.119.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.12.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.120.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.120.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.121.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.121.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.122.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.122.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.123.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.123.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.124.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.124.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.125.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.125.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.126.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.126.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.127.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.127.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.13.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.14.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.15.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.16.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.17.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.18.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.19.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.2.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.20.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.21.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.22.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.23.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.24.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.25.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.26.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.27.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.28.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.29.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.3.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.30.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.31.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.32.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.33.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.34.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.35.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.36.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.37.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.38.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.39.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.4.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.40.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.41.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.42.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.43.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.44.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.45.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.46.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.47.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.48.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.49.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.5.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.50.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.51.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.52.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.53.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.54.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.55.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.56.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.57.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.58.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.59.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.6.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.60.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.61.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.62.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.63.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.64.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.64.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.65.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.65.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.66.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.66.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.67.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.67.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.68.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.68.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.69.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.69.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.7.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.70.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.70.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.71.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.71.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.72.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.72.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.73.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.73.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.74.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.74.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.75.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.75.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.76.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.76.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.77.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.77.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.78.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.78.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.79.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.79.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.8.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.80.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.80.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.81.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.81.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.82.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.82.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.83.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.83.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.84.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.84.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.85.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.85.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.86.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.86.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.87.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.87.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.88.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.88.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.89.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.89.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.9.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.90.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.90.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.91.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.91.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.92.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.92.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.93.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.93.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.94.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.94.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.95.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.95.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.96.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.96.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.97.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.97.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.98.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.98.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.99.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.experts.99.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.gate.e_score_correction_bias": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.gate.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.shared_experts.down_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.shared_experts.gate_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00045-of-00048.safetensors",
+ "model.layers.43.mlp.shared_experts.up_proj.weight_scale": "model-00045-of-00048.safetensors",
+ "model.layers.5.mlp.experts.0.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.0.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.0.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.0.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.1.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.1.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.1.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.1.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.10.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.10.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.10.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.10.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.100.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.100.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.100.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.100.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.101.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.101.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.101.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.101.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.102.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.102.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.102.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.102.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.103.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.103.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.103.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.103.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.104.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.104.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.104.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.104.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.105.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.105.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.105.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.105.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.106.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.106.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.106.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.106.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.107.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.107.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.107.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.107.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.108.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.108.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.108.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.108.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.109.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.109.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.109.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.109.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.11.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.11.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.11.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.11.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.110.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.110.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.110.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.110.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.111.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.111.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.111.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.111.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.112.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.112.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.112.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.112.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.113.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.113.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.113.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.113.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.114.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.114.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.114.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.114.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.115.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.115.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.115.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.115.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.116.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.116.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.116.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.116.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.117.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.117.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.117.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.117.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.118.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.118.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.118.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.118.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.119.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.119.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.119.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.119.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.12.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.12.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.12.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.12.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.120.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.120.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.120.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.120.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.121.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.121.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.121.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.121.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.122.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.122.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.122.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.122.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.123.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.123.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.123.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.123.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.124.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.124.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.124.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.124.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.125.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.125.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.125.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.125.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.126.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.126.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.126.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.126.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.127.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.127.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.127.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.127.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.13.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.13.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.13.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.13.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.14.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.14.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.14.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.14.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.15.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.15.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.15.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.15.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.16.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.16.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.16.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.16.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.17.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.17.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.17.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.17.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.18.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.18.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.18.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.18.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.19.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.19.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.19.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.19.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.2.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.2.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.2.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.2.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.20.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.20.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.20.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.20.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.21.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.21.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.21.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.21.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.22.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.22.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.22.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.22.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.23.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.23.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.23.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.23.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.24.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.24.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.24.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.24.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.25.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.25.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.25.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.25.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.26.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.26.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.26.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.26.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.27.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.27.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.27.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.27.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.28.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.28.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.28.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.28.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.29.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.29.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.29.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.29.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.3.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.3.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.3.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.3.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.30.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.30.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.30.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.30.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.31.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.31.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.31.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.31.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.32.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.32.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.32.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.32.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.33.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.33.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.33.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.33.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.34.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.34.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.34.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.34.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.35.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.35.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.35.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.35.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.36.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.36.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.36.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.36.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.37.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.37.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.37.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.37.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.38.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.38.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.38.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.38.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.39.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.39.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.39.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.39.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.4.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.4.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.4.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.4.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.40.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.40.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.40.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.40.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.41.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.41.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.41.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.41.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.42.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.42.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.42.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.42.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.43.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.43.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.43.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.43.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.44.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.44.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.44.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.44.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.45.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.45.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.45.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.45.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.46.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.46.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.46.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.46.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.47.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.47.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.47.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.47.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.48.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.48.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.48.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.48.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.49.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.49.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.49.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.49.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.5.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.5.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.5.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.5.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.50.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.50.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.50.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.50.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.51.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.51.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.51.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.51.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.52.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.52.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.52.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.52.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.53.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.53.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.53.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.53.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.54.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.54.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.54.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.54.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.55.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.55.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.55.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.55.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.56.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.56.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.56.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.56.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.57.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.57.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.57.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.57.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.58.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.58.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.58.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.58.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.59.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.59.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.59.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.59.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.6.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.6.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.6.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.6.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.60.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.60.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.60.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.60.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.61.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.61.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.61.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.61.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.62.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.62.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.62.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.62.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.63.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.63.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.63.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.63.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.64.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.64.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.64.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.64.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.65.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.65.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.65.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.65.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.66.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.66.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.66.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.66.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.67.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.67.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.67.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.67.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.68.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.68.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.68.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.68.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.69.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.69.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.69.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.69.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.7.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.7.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.7.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.7.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.70.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.70.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.70.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.70.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.71.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.71.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.71.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.71.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.72.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.72.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.72.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.72.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.73.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.73.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.73.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.73.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.74.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.74.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.74.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.74.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.75.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.75.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.75.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.75.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.76.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.76.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.76.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.76.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.77.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.77.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.77.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.77.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.78.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.78.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.78.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.78.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.79.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.79.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.79.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.79.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.8.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.8.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.8.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.8.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.80.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.80.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.80.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.80.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.81.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.81.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.81.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.81.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.82.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.82.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.82.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.82.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.83.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.83.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.83.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.83.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.84.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.84.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.84.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.84.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.85.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.85.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.85.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.85.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.86.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.86.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.86.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.86.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.87.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.87.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.87.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.87.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.88.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.88.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.88.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.88.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.89.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.89.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.89.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.89.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.9.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.9.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.9.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.9.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.90.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.90.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.90.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.90.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.91.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.91.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.91.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.91.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.92.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.92.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.92.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.92.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.93.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.93.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.93.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.93.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.94.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.94.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.94.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.94.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.95.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.95.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.95.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.95.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.96.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.96.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.96.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.96.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.97.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.97.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.97.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.97.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.98.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.98.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.98.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.98.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.99.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.99.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.99.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.5.mlp.experts.99.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.0.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.1.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.10.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.100.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.101.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.102.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.103.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.104.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.105.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.106.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.107.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.108.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.109.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.11.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.110.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.111.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.112.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.113.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.114.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.115.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.116.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.117.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.118.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.119.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.12.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.120.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.121.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.122.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.123.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.124.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.125.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.126.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.127.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.13.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.14.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.15.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.16.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.17.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.18.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.19.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.2.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.20.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.21.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.22.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.23.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.24.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.25.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.26.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.27.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.28.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.29.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.3.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.30.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.31.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.32.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.33.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.34.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.35.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.36.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.37.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.38.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.39.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.4.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.40.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.41.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.42.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.43.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.44.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.45.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.46.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.47.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.48.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.49.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.5.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.50.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.51.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.52.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.53.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.54.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.55.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.56.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.57.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.58.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.59.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.6.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.60.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.61.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.62.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.63.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.64.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.65.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.66.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.67.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.68.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.69.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.7.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.70.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.71.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.72.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.73.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.74.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.75.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.76.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.77.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.78.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.79.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.8.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.80.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.81.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.82.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.83.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.84.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.85.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.86.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.87.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.88.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.89.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.9.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.90.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.91.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.92.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.93.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.94.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.95.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.96.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.97.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.98.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.experts.99.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.gate.e_score_correction_bias": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.gate.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.shared_experts.down_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.shared_experts.gate_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00008-of-00048.safetensors",
+ "model.layers.6.mlp.shared_experts.up_proj.weight_scale": "model-00008-of-00048.safetensors",
+ "model.layers.23.mlp.experts.0.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.0.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.0.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.0.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.1.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.1.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.1.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.1.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.10.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.10.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.10.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.10.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.100.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.100.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.100.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.100.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.101.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.101.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.101.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.101.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.102.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.102.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.102.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.102.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.103.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.103.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.103.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.103.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.104.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.104.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.104.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.104.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.105.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.105.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.105.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.105.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.106.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.106.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.106.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.106.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.107.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.107.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.107.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.107.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.108.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.108.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.108.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.108.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.109.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.109.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.109.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.109.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.11.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.11.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.11.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.11.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.110.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.110.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.110.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.110.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.111.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.111.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.111.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.111.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.112.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.112.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.112.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.112.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.113.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.113.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.113.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.113.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.114.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.114.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.114.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.114.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.115.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.115.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.115.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.115.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.116.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.116.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.116.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.116.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.117.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.117.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.117.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.117.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.118.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.118.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.118.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.118.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.119.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.119.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.119.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.119.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.12.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.12.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.12.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.12.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.120.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.120.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.120.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.120.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.121.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.121.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.121.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.121.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.122.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.122.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.122.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.122.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.123.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.123.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.123.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.123.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.124.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.124.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.124.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.124.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.125.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.125.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.125.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.125.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.126.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.126.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.126.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.126.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.127.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.127.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.127.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.127.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.13.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.13.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.13.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.13.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.14.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.14.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.14.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.14.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.15.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.15.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.15.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.15.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.16.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.16.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.16.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.16.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.17.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.17.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.17.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.17.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.18.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.18.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.18.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.18.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.19.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.19.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.19.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.19.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.2.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.2.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.2.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.2.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.20.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.20.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.20.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.20.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.21.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.21.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.21.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.21.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.22.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.22.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.22.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.22.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.23.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.23.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.23.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.23.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.24.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.24.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.24.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.24.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.25.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.25.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.25.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.25.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.26.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.26.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.26.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.26.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.27.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.27.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.27.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.27.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.28.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.28.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.28.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.28.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.29.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.29.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.29.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.29.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.3.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.3.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.3.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.3.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.30.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.30.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.30.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.30.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.31.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.31.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.31.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.31.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.32.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.32.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.32.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.32.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.33.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.33.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.33.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.33.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.34.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.34.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.34.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.34.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.35.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.35.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.35.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.35.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.36.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.36.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.36.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.36.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.37.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.37.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.37.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.37.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.38.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.38.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.38.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.38.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.39.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.39.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.39.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.39.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.4.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.4.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.4.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.4.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.40.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.40.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.40.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.40.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.41.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.41.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.41.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.41.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.42.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.42.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.42.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.42.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.43.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.43.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.43.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.43.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.44.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.44.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.44.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.44.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.45.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.45.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.45.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.45.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.46.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.46.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.46.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.46.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.47.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.47.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.47.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.47.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.48.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.48.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.48.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.48.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.49.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.49.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.49.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.49.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.5.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.5.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.5.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.5.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.50.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.50.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.50.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.50.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.51.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.51.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.51.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.51.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.52.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.52.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.52.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.52.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.53.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.53.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.53.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.53.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.54.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.54.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.54.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.54.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.55.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.55.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.55.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.55.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.56.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.56.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.56.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.56.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.57.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.57.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.57.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.57.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.58.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.58.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.58.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.58.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.59.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.59.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.59.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.59.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.6.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.6.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.6.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.6.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.60.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.60.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.60.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.60.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.61.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.61.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.61.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.61.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.62.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.62.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.62.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.62.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.63.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.63.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.63.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.63.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.64.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.64.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.64.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.64.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.65.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.65.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.65.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.65.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.66.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.66.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.66.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.66.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.67.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.67.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.67.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.67.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.68.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.68.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.68.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.68.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.69.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.69.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.69.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.69.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.7.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.7.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.7.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.7.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.70.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.70.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.70.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.70.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.71.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.71.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.71.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.71.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.72.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.72.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.72.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.72.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.73.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.73.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.73.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.73.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.74.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.74.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.74.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.74.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.75.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.75.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.75.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.75.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.76.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.76.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.76.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.76.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.77.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.77.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.77.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.77.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.78.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.78.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.78.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.78.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.79.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.79.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.79.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.79.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.8.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.8.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.8.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.8.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.80.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.80.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.80.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.80.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.81.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.81.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.81.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.81.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.82.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.82.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.82.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.82.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.83.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.83.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.83.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.83.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.84.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.84.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.84.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.84.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.85.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.85.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.85.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.85.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.86.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.86.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.86.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.86.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.87.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.87.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.87.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.87.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.88.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.88.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.88.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.88.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.89.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.89.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.89.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.89.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.9.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.9.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.9.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.9.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.90.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.90.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.90.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.90.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.91.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.91.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.91.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.91.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.92.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.92.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.92.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.92.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.93.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.93.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.93.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.93.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.94.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.94.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.94.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.94.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.95.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.95.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.95.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.95.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.96.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.96.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.96.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.96.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.97.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.97.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.97.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.97.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.98.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.98.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.98.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.98.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.99.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.99.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.99.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.23.mlp.experts.99.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.0.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.1.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.10.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.100.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.101.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.102.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.103.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.104.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.105.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.106.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.107.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.108.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.109.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.11.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.110.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.111.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.112.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.113.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.114.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.115.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.116.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.117.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.118.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.119.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.12.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.120.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.121.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.122.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.123.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.124.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.125.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.126.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.127.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.13.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.14.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.15.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.16.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.17.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.18.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.19.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.2.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.20.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.21.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.22.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.23.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.24.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.25.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.26.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.27.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.28.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.29.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.3.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.30.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.31.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.32.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.33.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.34.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.35.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.36.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.37.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.38.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.39.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.4.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.40.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.41.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.42.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.43.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.44.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.45.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.46.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.47.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.48.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.49.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.5.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.50.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.51.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.52.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.53.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.54.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.55.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.56.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.57.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.58.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.59.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.6.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.60.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.61.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.62.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.63.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.64.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.65.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.66.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.67.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.68.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.69.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.7.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.70.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.71.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.72.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.73.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.74.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.75.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.76.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.77.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.78.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.79.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.8.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.80.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.81.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.82.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.83.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.84.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.85.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.86.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.87.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.88.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.89.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.9.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.90.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.91.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.92.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.93.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.94.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.95.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.96.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.97.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.98.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.experts.99.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.gate.e_score_correction_bias": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.gate.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.shared_experts.down_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.shared_experts.gate_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00026-of-00048.safetensors",
+ "model.layers.24.mlp.shared_experts.up_proj.weight_scale": "model-00026-of-00048.safetensors",
+ "model.layers.3.mlp.experts.0.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.0.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.0.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.0.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.1.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.1.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.1.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.1.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.10.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.10.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.10.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.10.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.100.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.100.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.100.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.100.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.101.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.101.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.101.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.101.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.102.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.102.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.102.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.102.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.103.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.103.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.103.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.103.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.104.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.104.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.104.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.104.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.105.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.105.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.105.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.105.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.106.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.106.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.106.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.106.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.107.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.107.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.107.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.107.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.108.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.108.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.108.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.108.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.109.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.109.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.109.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.109.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.11.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.11.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.11.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.11.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.110.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.110.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.110.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.110.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.111.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.111.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.111.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.111.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.112.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.112.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.112.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.112.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.113.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.113.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.113.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.113.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.114.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.114.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.114.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.114.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.115.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.115.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.115.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.115.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.116.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.116.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.116.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.116.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.117.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.117.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.117.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.117.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.118.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.118.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.118.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.118.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.119.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.119.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.119.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.119.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.12.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.12.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.12.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.12.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.120.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.120.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.120.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.120.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.121.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.121.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.121.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.121.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.122.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.122.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.122.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.122.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.123.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.123.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.123.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.123.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.124.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.124.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.124.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.124.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.125.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.125.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.125.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.125.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.126.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.126.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.126.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.126.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.127.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.127.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.127.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.127.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.13.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.13.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.13.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.13.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.14.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.14.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.14.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.14.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.15.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.15.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.15.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.15.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.16.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.16.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.16.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.16.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.17.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.17.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.17.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.17.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.18.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.18.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.18.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.18.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.19.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.19.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.19.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.19.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.2.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.2.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.2.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.2.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.20.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.20.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.20.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.20.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.21.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.21.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.21.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.21.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.22.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.22.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.22.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.22.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.23.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.23.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.23.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.23.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.24.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.24.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.24.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.24.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.25.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.25.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.25.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.25.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.26.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.26.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.26.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.26.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.27.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.27.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.27.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.27.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.28.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.28.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.28.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.28.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.29.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.29.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.29.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.29.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.3.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.3.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.3.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.3.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.30.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.30.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.30.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.30.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.31.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.31.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.31.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.31.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.32.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.32.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.32.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.32.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.33.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.33.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.33.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.33.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.34.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.34.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.34.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.34.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.35.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.35.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.35.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.35.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.36.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.36.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.36.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.36.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.37.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.37.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.37.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.37.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.38.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.38.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.38.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.38.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.39.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.39.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.39.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.39.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.4.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.4.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.4.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.4.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.40.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.40.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.40.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.40.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.41.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.41.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.41.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.41.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.42.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.42.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.42.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.42.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.43.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.43.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.43.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.43.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.44.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.44.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.44.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.44.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.45.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.45.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.45.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.45.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.46.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.46.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.46.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.46.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.47.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.47.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.47.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.47.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.48.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.48.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.48.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.48.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.49.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.49.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.49.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.49.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.5.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.5.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.5.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.5.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.50.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.50.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.50.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.50.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.51.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.51.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.51.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.51.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.52.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.52.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.52.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.52.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.53.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.53.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.53.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.53.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.54.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.54.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.54.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.54.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.55.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.55.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.55.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.55.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.56.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.56.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.56.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.56.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.57.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.57.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.57.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.57.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.58.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.58.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.58.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.58.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.59.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.59.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.59.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.59.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.6.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.6.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.6.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.6.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.60.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.60.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.60.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.60.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.61.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.61.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.61.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.61.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.62.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.62.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.62.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.62.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.63.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.63.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.63.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.63.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.64.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.64.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.64.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.64.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.65.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.65.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.65.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.65.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.66.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.66.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.66.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.66.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.67.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.67.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.67.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.67.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.68.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.68.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.68.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.68.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.69.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.69.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.69.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.69.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.7.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.7.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.7.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.7.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.70.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.70.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.70.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.70.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.71.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.71.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.71.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.71.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.72.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.72.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.72.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.72.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.73.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.73.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.73.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.73.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.74.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.74.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.74.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.74.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.75.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.75.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.75.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.75.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.76.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.76.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.76.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.76.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.77.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.77.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.77.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.77.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.78.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.78.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.78.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.78.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.79.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.79.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.79.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.79.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.8.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.8.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.8.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.8.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.80.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.80.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.80.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.80.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.81.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.81.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.81.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.81.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.82.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.82.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.82.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.82.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.83.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.83.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.83.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.83.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.84.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.84.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.84.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.84.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.85.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.85.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.85.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.85.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.86.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.86.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.86.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.86.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.87.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.87.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.87.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.87.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.88.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.88.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.88.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.88.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.89.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.89.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.89.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.89.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.9.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.9.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.9.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.9.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.90.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.90.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.90.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.90.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.91.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.91.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.91.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.91.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.92.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.92.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.92.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.92.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.93.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.93.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.93.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.93.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.94.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.94.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.94.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.94.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.95.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.95.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.95.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.95.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.96.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.96.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.96.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.96.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.97.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.97.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.97.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.97.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.98.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.98.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.98.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.98.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.99.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.99.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.99.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.3.mlp.experts.99.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.0.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.1.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.10.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.100.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.101.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.102.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.103.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.104.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.105.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.106.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.107.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.108.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.109.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.11.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.110.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.111.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.112.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.113.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.114.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.115.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.116.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.117.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.118.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.119.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.12.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.120.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.121.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.122.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.123.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.124.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.125.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.126.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.127.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.13.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.14.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.15.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.16.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.17.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.18.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.19.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.2.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.20.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.21.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.22.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.23.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.24.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.25.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.26.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.27.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.28.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.29.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.3.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.30.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.31.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.32.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.33.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.34.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.35.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.36.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.37.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.38.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.39.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.4.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.40.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.41.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.42.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.43.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.44.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.45.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.46.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.47.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.48.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.49.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.5.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.50.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.51.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.52.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.53.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.54.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.55.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.56.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.57.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.58.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.59.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.6.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.60.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.61.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.62.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.63.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.64.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.65.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.66.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.67.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.68.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.69.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.7.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.70.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.71.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.72.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.73.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.74.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.75.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.76.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.77.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.78.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.79.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.8.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.80.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.81.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.82.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.83.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.84.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.85.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.86.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.87.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.88.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.89.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.9.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.90.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.91.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.92.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.93.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.94.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.95.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.96.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.97.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.98.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.experts.99.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.gate.e_score_correction_bias": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.gate.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.shared_experts.down_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.shared_experts.gate_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00006-of-00048.safetensors",
+ "model.layers.4.mlp.shared_experts.up_proj.weight_scale": "model-00006-of-00048.safetensors",
+ "model.layers.35.mlp.experts.0.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.0.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.0.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.0.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.1.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.1.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.1.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.1.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.10.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.10.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.10.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.10.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.100.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.100.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.100.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.100.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.101.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.101.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.101.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.101.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.102.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.102.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.102.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.102.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.103.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.103.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.103.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.103.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.104.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.104.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.104.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.104.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.105.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.105.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.105.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.105.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.106.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.106.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.106.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.106.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.107.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.107.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.107.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.107.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.108.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.108.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.108.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.108.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.109.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.109.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.109.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.109.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.11.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.11.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.11.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.11.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.110.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.110.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.110.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.110.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.111.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.111.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.111.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.111.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.112.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.112.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.112.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.112.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.113.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.113.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.113.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.113.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.114.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.114.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.114.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.114.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.115.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.115.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.115.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.115.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.116.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.116.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.116.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.116.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.117.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.117.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.117.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.117.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.118.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.118.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.118.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.118.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.119.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.119.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.119.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.119.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.12.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.12.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.12.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.12.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.120.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.120.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.120.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.120.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.121.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.121.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.121.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.121.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.122.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.122.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.122.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.122.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.123.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.123.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.123.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.123.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.124.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.124.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.124.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.124.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.125.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.125.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.125.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.125.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.126.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.126.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.126.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.126.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.127.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.127.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.127.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.127.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.13.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.13.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.13.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.13.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.14.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.14.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.14.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.14.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.15.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.15.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.15.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.15.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.16.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.16.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.16.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.16.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.17.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.17.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.17.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.17.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.18.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.18.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.18.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.18.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.19.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.19.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.19.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.19.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.2.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.2.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.2.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.2.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.20.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.20.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.20.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.20.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.21.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.21.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.21.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.21.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.22.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.22.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.22.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.22.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.23.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.23.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.23.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.23.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.24.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.24.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.24.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.24.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.25.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.25.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.25.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.25.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.26.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.26.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.26.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.26.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.27.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.27.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.27.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.27.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.28.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.28.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.28.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.28.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.29.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.29.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.29.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.29.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.3.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.3.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.3.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.3.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.30.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.30.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.30.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.30.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.31.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.31.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.31.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.31.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.32.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.32.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.32.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.32.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.33.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.33.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.33.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.33.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.34.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.34.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.34.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.34.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.35.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.35.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.35.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.35.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.36.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.36.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.36.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.36.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.37.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.37.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.37.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.37.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.38.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.38.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.38.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.38.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.39.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.39.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.39.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.39.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.4.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.4.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.4.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.4.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.40.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.40.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.40.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.40.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.41.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.41.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.41.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.41.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.42.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.42.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.42.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.42.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.43.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.43.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.43.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.43.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.44.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.44.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.44.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.44.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.45.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.45.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.45.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.45.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.46.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.46.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.46.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.46.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.47.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.47.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.47.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.47.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.48.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.48.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.48.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.48.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.49.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.49.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.49.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.49.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.5.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.5.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.5.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.5.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.50.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.50.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.50.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.50.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.51.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.51.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.51.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.51.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.52.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.52.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.52.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.52.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.53.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.53.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.53.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.53.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.54.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.54.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.54.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.54.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.55.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.55.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.55.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.55.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.56.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.56.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.56.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.56.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.57.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.57.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.57.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.57.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.58.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.58.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.58.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.58.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.59.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.59.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.59.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.59.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.6.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.6.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.6.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.6.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.60.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.60.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.60.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.60.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.61.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.61.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.61.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.61.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.62.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.62.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.62.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.62.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.63.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.63.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.63.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.63.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.64.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.64.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.64.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.64.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.65.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.65.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.65.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.65.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.66.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.66.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.66.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.66.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.67.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.67.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.67.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.67.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.68.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.68.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.68.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.68.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.69.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.69.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.69.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.69.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.7.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.7.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.7.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.7.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.70.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.70.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.70.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.70.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.71.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.71.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.71.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.71.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.72.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.72.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.72.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.72.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.73.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.73.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.73.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.73.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.74.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.74.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.74.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.74.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.75.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.75.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.75.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.75.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.76.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.76.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.76.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.76.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.77.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.77.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.77.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.77.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.78.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.78.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.78.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.78.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.79.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.79.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.79.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.79.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.8.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.8.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.8.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.8.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.80.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.80.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.80.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.80.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.81.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.81.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.81.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.81.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.82.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.82.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.82.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.82.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.83.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.83.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.83.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.83.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.84.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.84.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.84.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.84.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.85.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.85.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.85.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.85.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.86.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.86.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.86.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.86.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.87.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.87.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.87.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.87.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.88.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.88.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.88.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.88.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.89.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.89.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.89.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.89.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.9.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.9.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.9.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.9.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.90.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.90.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.90.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.90.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.91.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.91.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.91.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.91.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.92.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.92.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.92.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.92.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.93.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.93.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.93.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.93.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.94.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.94.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.94.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.94.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.95.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.95.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.95.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.95.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.96.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.96.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.96.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.96.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.97.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.97.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.97.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.97.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.98.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.98.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.98.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.98.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.99.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.99.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.99.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.35.mlp.experts.99.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.0.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.1.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.10.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.100.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.100.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.101.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.101.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.102.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.102.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.103.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.103.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.104.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.104.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.105.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.105.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.106.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.106.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.107.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.107.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.108.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.108.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.109.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.109.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.11.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.110.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.110.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.111.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.111.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.112.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.112.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.113.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.113.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.114.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.114.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.115.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.115.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.116.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.116.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.117.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.117.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.118.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.118.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.119.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.119.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.12.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.120.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.120.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.121.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.121.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.122.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.122.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.123.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.123.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.124.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.124.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.125.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.125.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.126.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.126.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.127.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.127.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.13.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.14.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.15.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.16.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.17.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.18.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.19.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.2.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.20.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.21.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.22.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.23.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.24.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.25.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.26.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.27.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.28.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.29.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.3.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.30.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.31.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.32.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.33.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.34.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.35.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.36.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.37.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.38.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.39.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.4.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.40.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.41.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.42.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.43.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.44.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.45.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.46.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.47.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.48.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.49.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.5.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.50.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.51.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.52.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.53.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.54.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.55.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.56.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.57.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.58.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.59.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.6.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.60.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.61.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.62.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.63.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.64.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.64.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.65.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.65.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.66.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.66.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.67.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.67.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.68.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.68.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.69.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.69.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.7.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.70.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.70.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.71.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.71.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.72.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.72.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.73.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.73.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.74.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.74.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.75.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.75.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.76.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.76.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.77.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.77.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.78.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.78.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.79.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.79.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.8.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.80.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.80.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.81.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.81.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.82.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.82.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.83.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.83.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.84.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.84.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.85.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.85.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.86.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.86.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.87.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.87.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.88.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.88.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.89.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.89.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.9.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.90.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.90.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.91.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.91.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.92.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.92.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.93.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.93.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.94.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.94.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.95.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.95.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.96.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.96.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.97.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.97.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.98.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.98.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.99.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.experts.99.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.gate.e_score_correction_bias": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.gate.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.shared_experts.down_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.shared_experts.gate_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00038-of-00048.safetensors",
+ "model.layers.36.mlp.shared_experts.up_proj.weight_scale": "model-00038-of-00048.safetensors",
+ "model.layers.43.mlp.experts.0.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.0.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.0.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.0.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.1.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.1.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.1.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.1.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.10.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.10.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.10.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.10.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.100.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.100.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.100.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.100.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.101.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.101.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.101.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.101.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.102.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.102.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.102.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.102.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.103.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.103.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.103.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.103.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.104.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.104.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.104.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.104.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.105.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.105.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.105.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.105.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.106.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.106.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.106.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.106.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.107.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.107.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.107.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.107.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.108.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.108.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.108.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.108.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.109.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.109.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.109.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.109.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.11.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.11.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.11.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.11.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.110.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.110.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.110.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.110.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.111.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.111.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.111.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.111.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.112.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.112.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.112.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.112.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.113.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.113.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.113.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.113.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.114.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.114.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.114.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.114.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.115.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.115.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.115.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.115.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.116.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.116.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.116.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.116.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.117.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.117.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.117.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.117.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.118.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.118.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.118.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.118.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.119.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.119.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.119.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.119.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.12.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.12.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.12.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.12.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.120.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.120.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.120.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.120.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.121.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.121.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.121.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.121.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.122.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.122.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.122.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.122.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.123.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.123.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.123.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.123.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.124.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.124.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.124.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.124.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.125.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.125.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.125.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.125.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.126.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.126.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.126.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.126.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.127.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.127.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.127.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.127.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.13.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.13.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.13.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.13.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.14.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.14.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.14.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.14.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.15.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.15.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.15.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.15.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.16.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.16.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.16.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.16.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.17.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.17.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.17.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.17.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.18.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.18.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.18.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.18.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.19.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.19.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.19.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.19.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.2.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.2.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.2.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.2.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.20.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.20.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.20.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.20.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.21.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.21.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.21.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.21.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.22.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.22.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.22.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.22.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.23.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.23.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.23.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.23.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.24.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.24.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.24.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.24.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.25.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.25.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.25.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.25.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.26.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.26.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.26.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.26.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.27.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.27.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.27.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.27.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.28.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.28.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.28.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.28.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.29.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.29.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.29.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.29.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.3.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.3.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.3.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.3.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.30.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.30.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.30.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.30.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.31.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.31.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.31.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.31.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.32.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.32.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.32.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.32.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.33.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.33.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.33.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.33.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.34.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.34.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.34.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.34.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.35.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.35.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.35.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.35.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.36.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.36.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.36.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.36.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.37.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.37.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.37.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.37.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.38.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.38.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.38.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.38.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.39.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.39.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.39.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.39.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.4.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.4.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.4.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.4.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.40.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.40.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.40.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.40.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.41.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.41.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.41.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.41.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.42.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.42.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.42.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.42.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.43.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.43.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.43.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.43.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.44.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.44.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.44.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.44.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.45.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.45.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.45.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.45.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.46.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.46.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.46.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.46.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.47.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.47.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.47.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.47.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.48.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.48.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.48.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.48.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.49.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.49.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.49.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.49.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.5.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.5.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.5.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.5.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.50.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.50.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.50.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.50.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.51.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.51.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.51.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.51.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.52.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.52.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.52.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.52.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.53.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.53.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.53.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.53.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.54.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.54.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.54.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.54.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.55.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.55.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.55.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.55.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.56.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.56.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.56.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.56.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.57.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.57.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.57.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.57.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.58.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.58.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.58.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.58.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.59.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.59.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.59.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.59.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.6.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.6.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.6.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.6.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.60.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.60.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.60.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.60.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.61.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.61.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.61.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.61.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.62.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.62.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.62.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.62.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.63.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.63.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.63.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.63.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.64.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.64.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.64.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.64.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.65.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.65.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.65.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.65.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.66.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.66.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.66.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.66.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.67.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.67.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.67.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.67.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.68.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.68.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.68.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.68.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.69.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.69.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.69.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.69.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.7.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.7.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.7.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.7.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.70.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.70.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.70.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.70.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.71.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.71.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.71.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.71.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.72.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.72.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.72.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.72.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.73.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.73.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.73.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.73.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.74.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.74.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.74.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.74.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.75.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.75.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.75.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.75.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.76.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.76.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.76.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.76.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.77.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.77.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.77.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.77.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.78.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.78.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.78.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.78.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.79.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.79.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.79.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.79.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.8.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.8.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.8.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.8.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.80.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.80.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.80.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.80.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.81.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.81.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.81.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.81.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.82.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.82.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.82.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.82.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.83.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.83.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.83.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.83.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.84.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.84.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.84.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.84.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.85.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.85.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.85.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.85.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.86.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.86.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.86.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.86.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.87.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.87.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.87.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.87.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.88.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.88.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.88.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.88.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.89.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.89.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.89.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.89.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.9.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.9.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.9.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.9.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.90.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.90.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.90.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.90.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.91.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.91.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.91.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.91.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.92.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.92.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.92.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.92.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.93.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.93.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.93.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.93.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.94.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.94.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.94.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.94.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.95.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.95.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.95.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.95.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.96.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.96.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.96.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.96.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.97.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.97.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.97.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.97.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.98.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.98.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.98.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.98.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.99.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.99.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.99.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.43.mlp.experts.99.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.0.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.1.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.10.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.100.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.100.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.101.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.101.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.102.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.102.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.103.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.103.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.104.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.104.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.105.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.105.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.106.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.106.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.107.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.107.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.108.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.108.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.109.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.109.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.11.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.110.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.110.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.111.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.111.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.112.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.112.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.113.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.113.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.114.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.114.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.115.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.115.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.116.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.116.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.117.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.117.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.118.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.118.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.119.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.119.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.12.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.120.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.120.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.121.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.121.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.122.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.122.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.123.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.123.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.124.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.124.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.125.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.125.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.126.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.126.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.127.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.127.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.13.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.14.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.15.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.16.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.17.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.18.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.19.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.2.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.20.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.21.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.22.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.23.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.24.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.25.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.26.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.27.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.28.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.29.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.3.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.30.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.31.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.32.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.33.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.34.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.35.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.36.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.37.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.38.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.39.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.4.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.40.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.41.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.42.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.43.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.44.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.45.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.46.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.47.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.48.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.49.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.5.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.50.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.51.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.52.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.53.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.54.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.55.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.56.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.57.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.58.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.59.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.6.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.60.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.61.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.62.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.63.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.64.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.64.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.65.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.65.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.66.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.66.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.67.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.67.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.68.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.68.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.69.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.69.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.7.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.70.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.70.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.71.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.71.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.72.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.72.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.73.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.73.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.74.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.74.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.75.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.75.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.76.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.76.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.77.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.77.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.78.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.78.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.79.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.79.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.8.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.80.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.80.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.81.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.81.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.82.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.82.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.83.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.83.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.84.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.84.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.85.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.85.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.86.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.86.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.87.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.87.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.88.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.88.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.89.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.89.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.9.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.90.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.90.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.91.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.91.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.92.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.92.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.93.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.93.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.94.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.94.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.95.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.95.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.96.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.96.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.97.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.97.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.98.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.98.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.99.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.experts.99.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.gate.e_score_correction_bias": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.gate.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.shared_experts.down_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.shared_experts.gate_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00046-of-00048.safetensors",
+ "model.layers.44.mlp.shared_experts.up_proj.weight_scale": "model-00046-of-00048.safetensors",
+ "model.layers.16.mlp.experts.0.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.0.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.0.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.0.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.1.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.1.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.1.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.1.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.10.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.10.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.10.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.10.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.100.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.100.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.100.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.100.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.101.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.101.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.101.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.101.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.102.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.102.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.102.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.102.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.103.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.103.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.103.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.103.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.104.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.104.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.104.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.104.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.105.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.105.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.105.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.105.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.106.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.106.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.106.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.106.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.107.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.107.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.107.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.107.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.108.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.108.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.108.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.108.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.109.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.109.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.109.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.109.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.11.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.11.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.11.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.11.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.110.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.110.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.110.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.110.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.111.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.111.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.111.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.111.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.112.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.112.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.112.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.112.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.113.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.113.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.113.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.113.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.114.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.114.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.114.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.114.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.115.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.115.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.115.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.115.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.116.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.116.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.116.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.116.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.117.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.117.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.117.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.117.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.118.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.118.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.118.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.118.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.119.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.119.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.119.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.119.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.12.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.12.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.12.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.12.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.120.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.120.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.120.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.120.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.121.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.121.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.121.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.121.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.122.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.122.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.122.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.122.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.123.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.123.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.123.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.123.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.124.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.124.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.124.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.124.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.125.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.125.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.125.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.125.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.126.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.126.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.126.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.126.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.127.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.127.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.127.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.127.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.13.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.13.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.13.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.13.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.14.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.14.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.14.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.14.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.15.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.15.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.15.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.15.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.16.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.16.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.16.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.16.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.17.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.17.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.17.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.17.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.18.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.18.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.18.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.18.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.19.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.19.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.19.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.19.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.2.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.2.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.2.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.2.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.20.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.20.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.20.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.20.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.21.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.21.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.21.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.21.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.22.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.22.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.22.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.22.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.23.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.23.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.23.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.23.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.24.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.24.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.24.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.24.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.25.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.25.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.25.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.25.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.26.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.26.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.26.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.26.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.27.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.27.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.27.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.27.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.28.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.28.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.28.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.28.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.29.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.29.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.29.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.29.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.3.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.3.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.3.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.3.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.30.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.30.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.30.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.30.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.31.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.31.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.31.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.31.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.32.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.32.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.32.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.32.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.33.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.33.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.33.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.33.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.34.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.34.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.34.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.34.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.35.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.35.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.35.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.35.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.36.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.36.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.36.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.36.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.37.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.37.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.37.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.37.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.38.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.38.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.38.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.38.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.39.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.39.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.39.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.39.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.4.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.4.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.4.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.4.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.40.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.40.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.40.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.40.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.41.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.41.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.41.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.41.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.42.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.42.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.42.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.42.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.43.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.43.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.43.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.43.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.44.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.44.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.44.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.44.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.45.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.45.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.45.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.45.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.46.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.46.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.46.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.46.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.47.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.47.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.47.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.47.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.48.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.48.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.48.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.48.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.49.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.49.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.49.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.49.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.5.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.5.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.5.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.5.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.50.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.50.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.50.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.50.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.51.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.51.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.51.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.51.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.52.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.52.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.52.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.52.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.53.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.53.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.53.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.53.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.54.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.54.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.54.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.54.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.55.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.55.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.55.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.55.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.56.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.56.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.56.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.56.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.57.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.57.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.57.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.57.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.58.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.58.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.58.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.58.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.59.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.59.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.59.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.59.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.6.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.6.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.6.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.6.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.60.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.60.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.60.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.60.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.61.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.61.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.61.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.61.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.62.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.62.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.62.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.62.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.63.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.63.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.63.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.63.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.64.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.64.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.64.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.64.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.65.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.65.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.65.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.65.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.66.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.66.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.66.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.66.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.67.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.67.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.67.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.67.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.68.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.68.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.68.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.68.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.69.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.69.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.69.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.69.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.7.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.7.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.7.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.7.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.70.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.70.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.70.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.70.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.71.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.71.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.71.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.71.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.72.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.72.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.72.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.72.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.73.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.73.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.73.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.73.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.74.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.74.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.74.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.74.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.75.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.75.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.75.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.75.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.76.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.76.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.76.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.76.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.77.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.77.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.77.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.77.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.78.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.78.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.78.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.78.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.79.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.79.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.79.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.79.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.8.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.8.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.8.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.8.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.80.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.80.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.80.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.80.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.81.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.81.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.81.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.81.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.82.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.82.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.82.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.82.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.83.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.83.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.83.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.83.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.84.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.84.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.84.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.84.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.85.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.85.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.85.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.85.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.86.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.86.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.86.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.86.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.87.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.87.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.87.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.87.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.88.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.88.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.88.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.88.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.89.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.89.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.89.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.89.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.9.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.9.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.9.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.9.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.90.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.90.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.90.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.90.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.91.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.91.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.91.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.91.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.92.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.92.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.92.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.92.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.93.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.93.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.93.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.93.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.94.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.94.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.94.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.94.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.95.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.95.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.95.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.95.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.96.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.96.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.96.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.96.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.97.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.97.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.97.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.97.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.98.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.98.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.98.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.98.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.99.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.99.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.99.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.16.mlp.experts.99.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.0.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.1.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.10.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.100.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.101.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.102.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.103.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.104.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.105.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.106.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.107.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.108.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.109.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.11.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.110.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.111.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.112.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.113.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.114.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.115.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.116.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.117.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.118.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.119.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.12.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.120.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.121.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.122.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.123.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.124.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.125.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.126.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.127.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.13.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.14.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.15.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.16.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.17.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.18.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.19.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.2.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.20.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.21.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.22.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.23.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.24.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.25.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.26.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.27.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.28.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.29.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.3.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.30.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.31.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.32.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.33.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.34.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.35.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.36.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.37.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.38.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.39.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.4.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.40.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.41.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.42.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.43.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.44.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.45.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.46.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.47.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.48.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.49.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.5.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.50.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.51.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.52.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.53.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.54.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.55.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.56.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.57.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.58.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.59.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.6.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.60.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.61.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.62.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.63.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.64.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.65.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.66.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.67.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.68.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.69.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.7.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.70.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.71.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.72.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.73.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.74.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.75.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.76.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.77.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.78.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.79.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.8.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.80.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.81.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.82.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.83.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.84.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.85.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.86.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.87.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.88.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.89.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.9.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.90.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.91.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.92.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.93.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.94.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.95.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.96.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.97.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.98.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.experts.99.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.gate.e_score_correction_bias": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.gate.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.shared_experts.down_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.shared_experts.gate_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00019-of-00048.safetensors",
+ "model.layers.17.mlp.shared_experts.up_proj.weight_scale": "model-00019-of-00048.safetensors",
+ "model.layers.32.mlp.experts.0.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.0.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.0.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.0.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.1.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.1.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.1.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.1.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.10.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.10.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.10.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.10.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.100.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.100.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.100.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.100.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.101.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.101.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.101.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.101.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.102.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.102.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.102.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.102.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.103.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.103.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.103.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.103.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.104.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.104.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.104.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.104.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.105.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.105.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.105.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.105.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.106.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.106.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.106.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.106.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.107.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.107.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.107.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.107.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.108.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.108.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.108.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.108.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.109.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.109.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.109.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.109.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.11.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.11.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.11.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.11.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.110.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.110.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.110.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.110.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.111.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.111.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.111.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.111.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.112.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.112.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.112.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.112.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.113.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.113.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.113.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.113.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.114.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.114.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.114.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.114.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.115.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.115.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.115.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.115.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.116.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.116.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.116.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.116.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.117.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.117.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.117.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.117.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.118.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.118.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.118.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.118.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.119.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.119.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.119.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.119.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.12.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.12.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.12.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.12.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.120.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.120.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.120.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.120.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.121.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.121.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.121.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.121.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.122.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.122.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.122.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.122.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.123.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.123.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.123.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.123.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.124.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.124.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.124.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.124.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.125.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.125.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.125.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.125.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.126.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.126.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.126.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.126.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.127.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.127.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.127.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.127.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.13.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.13.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.13.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.13.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.14.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.14.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.14.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.14.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.15.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.15.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.15.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.15.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.16.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.16.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.16.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.16.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.17.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.17.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.17.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.17.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.18.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.18.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.18.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.18.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.19.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.19.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.19.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.19.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.2.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.2.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.2.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.2.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.20.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.20.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.20.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.20.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.21.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.21.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.21.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.21.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.22.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.22.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.22.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.22.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.23.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.23.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.23.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.23.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.24.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.24.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.24.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.24.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.25.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.25.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.25.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.25.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.26.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.26.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.26.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.26.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.27.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.27.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.27.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.27.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.28.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.28.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.28.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.28.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.29.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.29.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.29.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.29.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.3.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.3.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.3.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.3.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.30.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.30.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.30.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.30.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.31.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.31.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.31.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.31.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.32.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.32.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.32.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.32.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.33.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.33.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.33.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.33.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.34.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.34.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.34.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.34.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.35.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.35.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.35.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.35.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.36.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.36.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.36.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.36.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.37.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.37.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.37.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.37.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.38.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.38.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.38.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.38.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.39.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.39.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.39.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.39.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.4.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.4.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.4.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.4.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.40.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.40.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.40.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.40.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.41.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.41.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.41.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.41.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.42.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.42.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.42.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.42.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.43.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.43.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.43.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.43.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.44.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.44.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.44.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.44.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.45.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.45.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.45.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.45.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.46.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.46.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.46.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.46.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.47.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.47.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.47.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.47.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.48.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.48.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.48.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.48.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.49.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.49.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.49.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.49.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.5.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.5.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.5.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.5.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.50.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.50.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.50.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.50.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.51.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.51.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.51.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.51.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.52.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.52.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.52.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.52.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.53.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.53.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.53.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.53.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.54.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.54.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.54.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.54.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.55.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.55.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.55.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.55.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.56.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.56.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.56.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.56.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.57.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.57.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.57.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.57.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.58.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.58.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.58.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.58.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.59.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.59.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.59.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.59.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.6.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.6.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.6.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.6.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.60.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.60.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.60.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.60.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.61.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.61.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.61.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.61.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.62.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.62.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.62.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.62.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.63.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.63.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.63.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.63.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.64.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.64.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.64.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.64.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.65.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.65.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.65.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.65.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.66.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.66.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.66.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.66.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.67.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.67.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.67.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.67.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.68.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.68.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.68.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.68.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.69.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.69.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.69.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.69.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.7.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.7.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.7.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.7.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.70.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.70.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.70.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.70.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.71.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.71.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.71.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.71.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.72.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.72.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.72.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.72.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.73.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.73.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.73.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.73.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.74.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.74.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.74.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.74.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.75.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.75.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.75.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.75.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.76.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.76.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.76.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.76.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.77.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.77.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.77.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.77.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.78.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.78.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.78.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.78.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.79.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.79.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.79.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.79.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.8.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.8.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.8.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.8.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.80.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.80.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.80.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.80.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.81.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.81.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.81.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.81.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.82.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.82.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.82.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.82.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.83.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.83.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.83.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.83.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.84.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.84.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.84.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.84.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.85.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.85.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.85.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.85.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.86.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.86.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.86.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.86.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.87.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.87.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.87.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.87.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.88.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.88.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.88.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.88.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.89.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.89.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.89.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.89.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.9.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.9.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.9.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.9.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.90.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.90.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.90.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.90.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.91.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.91.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.91.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.91.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.92.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.92.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.92.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.92.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.93.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.93.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.93.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.93.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.94.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.94.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.94.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.94.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.95.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.95.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.95.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.95.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.96.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.96.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.96.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.96.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.97.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.97.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.97.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.97.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.98.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.98.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.98.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.98.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.99.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.99.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.99.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.32.mlp.experts.99.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.0.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.1.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.10.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.100.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.100.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.101.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.101.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.102.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.102.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.103.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.103.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.104.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.104.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.105.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.105.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.106.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.106.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.107.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.107.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.108.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.108.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.109.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.109.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.11.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.110.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.110.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.111.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.111.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.112.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.112.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.113.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.113.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.114.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.114.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.115.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.115.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.116.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.116.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.117.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.117.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.118.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.118.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.119.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.119.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.12.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.120.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.120.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.121.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.121.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.122.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.122.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.123.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.123.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.124.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.124.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.125.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.125.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.126.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.126.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.127.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.127.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.13.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.14.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.15.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.16.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.17.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.18.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.19.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.2.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.20.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.21.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.22.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.23.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.24.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.25.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.26.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.27.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.28.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.29.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.3.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.30.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.31.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.32.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.33.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.34.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.35.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.36.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.37.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.38.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.39.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.4.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.40.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.41.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.42.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.43.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.44.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.45.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.46.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.47.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.48.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.49.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.5.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.50.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.51.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.52.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.53.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.54.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.55.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.56.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.57.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.58.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.59.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.6.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.60.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.61.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.62.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.63.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.64.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.64.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.65.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.65.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.66.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.66.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.67.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.67.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.68.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.68.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.69.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.69.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.7.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.70.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.70.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.71.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.71.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.72.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.72.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.73.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.73.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.74.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.74.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.75.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.75.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.76.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.76.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.77.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.77.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.78.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.78.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.79.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.79.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.8.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.80.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.80.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.81.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.81.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.82.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.82.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.83.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.83.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.84.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.84.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.85.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.85.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.86.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.86.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.87.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.87.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.88.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.88.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.89.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.89.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.9.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.90.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.90.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.91.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.91.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.92.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.92.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.93.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.93.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.94.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.94.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.95.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.95.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.96.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.96.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.97.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.97.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.98.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.98.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.99.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.experts.99.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.gate.e_score_correction_bias": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.gate.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.shared_experts.down_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.shared_experts.gate_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00035-of-00048.safetensors",
+ "model.layers.33.mlp.shared_experts.up_proj.weight_scale": "model-00035-of-00048.safetensors",
+ "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.0.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.1.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.10.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.100.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.101.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.102.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.103.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.104.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.105.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.106.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.107.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.108.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.109.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.11.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.110.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.111.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.112.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.113.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.114.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.115.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.116.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.117.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.118.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.119.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.12.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.120.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.121.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.122.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.123.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.124.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.125.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.126.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.127.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.13.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.14.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.15.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.16.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.17.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.18.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.19.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.2.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.20.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.21.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.22.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.23.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.24.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.25.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.26.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.27.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.28.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.29.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.3.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.30.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.31.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.32.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.33.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.34.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.35.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.36.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.37.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.38.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.39.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.4.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.40.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.41.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.42.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.43.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.44.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.45.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.46.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.47.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.48.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.49.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.5.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.50.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.51.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.52.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.53.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.54.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.55.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.56.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.57.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.58.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.59.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.6.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.60.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.61.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.62.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.63.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.64.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.65.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.66.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.67.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.68.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.69.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.7.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.70.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.71.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.72.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.73.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.74.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.75.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.76.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.77.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.78.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.79.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.8.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.80.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.81.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.82.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.83.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.84.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.85.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.86.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.87.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.88.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.89.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.9.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.90.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.91.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.92.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.93.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.94.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.95.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.96.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.97.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.98.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.experts.99.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.gate.e_score_correction_bias": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.gate.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.shared_experts.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.shared_experts.gate_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.10.mlp.shared_experts.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.0.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.0.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.0.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.0.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.1.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.1.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.1.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.1.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.10.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.10.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.10.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.10.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.100.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.100.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.100.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.100.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.101.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.101.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.101.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.101.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.102.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.102.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.102.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.102.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.103.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.103.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.103.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.103.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.104.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.104.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.104.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.104.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.105.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.105.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.105.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.105.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.106.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.106.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.106.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.106.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.107.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.107.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.107.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.107.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.108.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.108.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.108.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.108.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.109.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.109.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.109.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.109.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.11.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.11.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.11.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.11.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.110.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.110.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.110.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.110.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.111.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.111.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.111.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.111.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.112.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.112.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.112.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.112.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.113.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.113.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.113.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.113.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.114.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.114.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.114.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.114.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.115.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.115.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.115.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.115.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.116.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.116.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.116.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.116.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.117.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.117.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.117.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.117.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.118.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.118.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.118.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.118.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.119.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.119.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.119.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.119.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.12.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.12.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.12.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.12.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.120.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.120.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.120.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.120.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.121.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.121.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.121.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.121.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.122.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.122.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.122.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.122.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.123.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.123.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.123.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.123.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.124.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.124.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.124.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.124.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.125.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.125.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.125.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.125.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.126.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.126.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.126.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.126.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.127.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.127.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.127.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.127.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.13.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.13.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.13.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.13.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.14.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.14.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.14.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.14.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.15.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.15.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.15.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.15.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.16.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.16.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.16.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.16.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.17.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.17.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.17.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.17.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.18.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.18.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.18.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.18.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.19.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.19.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.19.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.19.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.2.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.2.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.2.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.2.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.20.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.20.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.20.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.20.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.21.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.21.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.21.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.21.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.22.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.22.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.22.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.22.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.23.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.23.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.23.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.23.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.24.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.24.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.24.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.24.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.25.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.25.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.25.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.25.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.26.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.26.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.26.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.26.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.27.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.27.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.27.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.27.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.28.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.28.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.28.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.28.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.29.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.29.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.29.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.29.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.3.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.3.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.3.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.3.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.30.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.30.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.30.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.30.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.31.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.31.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.31.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.31.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.32.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.32.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.32.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.32.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.33.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.33.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.33.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.33.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.34.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.34.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.34.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.34.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.35.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.35.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.35.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.35.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.36.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.36.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.36.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.36.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.37.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.37.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.37.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.37.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.38.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.38.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.38.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.38.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.39.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.39.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.39.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.39.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.4.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.4.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.4.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.4.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.40.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.40.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.40.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.40.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.41.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.41.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.41.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.41.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.42.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.42.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.42.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.42.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.43.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.43.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.43.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.43.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.44.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.44.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.44.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.44.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.45.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.45.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.45.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.45.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.46.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.46.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.46.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.46.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.47.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.47.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.47.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.47.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.48.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.48.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.48.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.48.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.49.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.49.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.49.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.49.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.5.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.5.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.5.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.5.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.50.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.50.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.50.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.50.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.51.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.51.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.51.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.51.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.52.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.52.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.52.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.52.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.53.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.53.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.53.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.53.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.54.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.54.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.54.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.54.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.55.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.55.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.55.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.55.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.56.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.56.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.56.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.56.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.57.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.57.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.57.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.57.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.58.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.58.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.58.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.58.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.59.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.59.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.59.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.59.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.6.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.6.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.6.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.6.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.60.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.60.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.60.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.60.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.61.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.61.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.61.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.61.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.62.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.62.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.62.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.62.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.63.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.63.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.63.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.63.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.64.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.64.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.64.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.64.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.65.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.65.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.65.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.65.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.66.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.66.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.66.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.66.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.67.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.67.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.67.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.67.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.68.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.68.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.68.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.68.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.69.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.69.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.69.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.69.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.7.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.7.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.7.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.7.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.70.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.70.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.70.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.70.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.71.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.71.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.71.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.71.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.72.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.72.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.72.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.72.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.73.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.73.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.73.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.73.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.74.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.74.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.74.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.74.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.75.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.75.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.75.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.75.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.76.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.76.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.76.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.76.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.77.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.77.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.77.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.77.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.78.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.78.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.78.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.78.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.79.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.79.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.79.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.79.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.8.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.8.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.8.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.8.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.80.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.80.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.80.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.80.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.81.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.81.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.81.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.81.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.82.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.82.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.82.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.82.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.83.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.83.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.83.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.83.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.84.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.84.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.84.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.84.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.85.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.85.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.85.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.85.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.86.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.86.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.86.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.86.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.87.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.87.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.87.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.87.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.88.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.88.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.88.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.88.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.89.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.89.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.89.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.89.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.9.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.9.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.9.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.9.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.90.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.90.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.90.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.90.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.91.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.91.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.91.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.91.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.92.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.92.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.92.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.92.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.93.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.93.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.93.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.93.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.94.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.94.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.94.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.94.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.95.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.95.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.95.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.95.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.96.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.96.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.96.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.96.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.97.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.97.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.97.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.97.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.98.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.98.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.98.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.98.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.99.down_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.99.down_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.99.up_proj.weight": "model-00012-of-00048.safetensors",
+ "model.layers.9.mlp.experts.99.up_proj.weight_scale": "model-00012-of-00048.safetensors",
+ "model.layers.14.mlp.experts.0.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.0.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.0.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.0.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.1.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.1.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.1.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.1.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.10.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.10.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.10.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.10.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.100.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.100.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.100.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.100.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.101.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.101.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.101.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.101.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.102.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.102.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.102.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.102.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.103.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.103.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.103.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.103.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.104.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.104.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.104.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.104.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.105.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.105.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.105.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.105.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.106.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.106.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.106.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.106.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.107.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.107.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.107.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.107.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.108.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.108.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.108.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.108.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.109.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.109.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.109.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.109.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.11.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.11.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.11.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.11.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.110.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.110.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.110.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.110.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.111.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.111.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.111.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.111.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.112.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.112.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.112.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.112.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.113.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.113.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.113.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.113.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.114.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.114.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.114.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.114.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.115.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.115.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.115.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.115.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.116.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.116.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.116.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.116.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.117.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.117.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.117.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.117.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.118.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.118.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.118.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.118.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.119.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.119.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.119.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.119.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.12.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.12.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.12.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.12.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.120.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.120.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.120.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.120.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.121.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.121.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.121.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.121.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.122.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.122.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.122.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.122.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.123.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.123.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.123.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.123.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.124.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.124.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.124.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.124.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.125.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.125.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.125.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.125.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.126.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.126.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.126.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.126.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.127.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.127.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.127.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.127.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.13.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.13.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.13.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.13.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.14.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.14.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.14.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.14.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.15.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.15.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.15.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.15.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.16.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.16.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.16.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.16.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.17.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.17.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.17.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.17.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.18.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.18.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.18.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.18.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.19.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.19.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.19.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.19.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.2.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.2.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.2.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.2.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.20.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.20.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.20.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.20.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.21.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.21.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.21.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.21.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.22.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.22.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.22.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.22.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.23.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.23.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.23.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.23.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.24.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.24.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.24.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.24.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.25.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.25.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.25.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.25.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.26.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.26.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.26.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.26.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.27.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.27.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.27.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.27.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.28.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.28.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.28.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.28.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.29.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.29.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.29.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.29.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.3.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.3.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.3.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.3.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.30.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.30.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.30.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.30.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.31.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.31.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.31.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.31.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.32.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.32.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.32.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.32.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.33.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.33.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.33.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.33.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.34.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.34.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.34.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.34.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.35.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.35.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.35.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.35.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.36.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.36.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.36.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.36.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.37.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.37.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.37.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.37.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.38.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.38.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.38.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.38.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.39.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.39.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.39.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.39.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.4.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.4.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.4.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.4.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.40.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.40.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.40.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.40.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.41.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.41.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.41.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.41.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.42.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.42.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.42.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.42.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.43.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.43.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.43.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.43.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.44.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.44.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.44.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.44.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.45.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.45.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.45.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.45.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.46.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.46.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.46.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.46.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.47.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.47.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.47.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.47.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.48.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.48.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.48.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.48.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.49.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.49.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.49.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.49.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.5.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.5.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.5.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.5.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.50.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.50.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.50.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.50.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.51.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.51.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.51.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.51.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.52.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.52.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.52.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.52.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.53.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.53.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.53.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.53.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.54.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.54.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.54.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.54.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.55.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.55.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.55.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.55.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.56.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.56.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.56.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.56.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.57.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.57.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.57.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.57.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.58.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.58.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.58.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.58.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.59.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.59.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.59.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.59.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.6.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.6.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.6.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.6.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.60.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.60.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.60.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.60.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.61.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.61.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.61.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.61.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.62.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.62.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.62.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.62.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.63.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.63.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.63.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.63.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.64.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.64.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.64.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.64.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.65.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.65.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.65.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.65.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.66.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.66.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.66.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.66.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.67.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.67.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.67.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.67.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.68.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.68.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.68.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.68.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.69.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.69.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.69.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.69.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.7.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.7.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.7.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.7.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.70.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.70.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.70.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.70.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.71.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.71.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.71.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.71.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.72.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.72.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.72.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.72.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.73.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.73.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.73.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.73.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.74.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.74.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.74.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.74.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.75.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.75.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.75.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.75.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.76.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.76.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.76.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.76.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.77.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.77.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.77.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.77.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.78.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.78.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.78.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.78.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.79.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.79.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.79.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.79.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.8.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.8.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.8.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.8.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.80.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.80.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.80.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.80.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.81.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.81.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.81.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.81.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.82.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.82.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.82.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.82.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.83.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.83.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.83.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.83.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.84.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.84.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.84.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.84.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.85.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.85.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.85.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.85.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.86.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.86.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.86.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.86.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.87.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.87.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.87.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.87.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.88.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.88.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.88.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.88.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.89.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.89.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.89.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.89.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.9.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.9.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.9.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.9.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.90.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.90.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.90.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.90.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.91.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.91.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.91.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.91.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.92.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.92.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.92.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.92.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.93.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.93.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.93.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.93.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.94.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.94.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.94.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.94.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.95.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.95.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.95.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.95.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.96.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.96.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.96.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.96.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.97.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.97.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.97.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.97.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.98.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.98.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.98.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.98.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.99.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.99.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.99.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.14.mlp.experts.99.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.0.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.1.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.10.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.100.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.101.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.102.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.103.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.104.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.105.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.106.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.107.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.108.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.109.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.11.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.110.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.111.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.112.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.113.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.114.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.115.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.116.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.117.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.118.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.119.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.12.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.120.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.121.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.122.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.123.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.124.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.125.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.126.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.127.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.13.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.14.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.15.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.16.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.17.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.18.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.19.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.2.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.20.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.21.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.22.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.23.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.24.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.25.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.26.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.27.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.28.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.29.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.3.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.30.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.31.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.32.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.33.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.34.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.35.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.36.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.37.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.38.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.39.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.4.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.40.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.41.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.42.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.43.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.44.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.45.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.46.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.47.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.48.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.49.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.5.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.50.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.51.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.52.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.53.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.54.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.55.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.56.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.57.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.58.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.59.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.6.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.60.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.61.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.62.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.63.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.64.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.65.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.66.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.67.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.68.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.69.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.7.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.70.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.71.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.72.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.73.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.74.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.75.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.76.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.77.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.78.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.79.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.8.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.80.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.81.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.82.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.83.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.84.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.85.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.86.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.87.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.88.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.89.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.9.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.90.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.91.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.92.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.93.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.94.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.95.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.96.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.97.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.98.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.experts.99.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.gate.e_score_correction_bias": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.gate.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.shared_experts.down_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.shared_experts.gate_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00017-of-00048.safetensors",
+ "model.layers.15.mlp.shared_experts.up_proj.weight_scale": "model-00017-of-00048.safetensors",
+ "model.layers.26.mlp.experts.0.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.0.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.0.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.0.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.1.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.1.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.1.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.1.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.10.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.10.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.10.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.10.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.100.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.100.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.100.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.100.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.101.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.101.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.101.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.101.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.102.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.102.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.102.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.102.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.103.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.103.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.103.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.103.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.104.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.104.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.104.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.104.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.105.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.105.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.105.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.105.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.106.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.106.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.106.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.106.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.107.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.107.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.107.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.107.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.108.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.108.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.108.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.108.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.109.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.109.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.109.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.109.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.11.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.11.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.11.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.11.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.110.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.110.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.110.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.110.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.111.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.111.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.111.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.111.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.112.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.112.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.112.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.112.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.113.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.113.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.113.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.113.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.114.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.114.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.114.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.114.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.115.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.115.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.115.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.115.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.116.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.116.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.116.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.116.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.117.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.117.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.117.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.117.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.118.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.118.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.118.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.118.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.119.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.119.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.119.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.119.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.12.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.12.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.12.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.12.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.120.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.120.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.120.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.120.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.121.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.121.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.121.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.121.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.122.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.122.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.122.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.122.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.123.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.123.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.123.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.123.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.124.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.124.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.124.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.124.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.125.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.125.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.125.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.125.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.126.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.126.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.126.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.126.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.127.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.127.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.127.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.127.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.13.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.13.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.13.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.13.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.14.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.14.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.14.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.14.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.15.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.15.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.15.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.15.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.16.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.16.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.16.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.16.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.17.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.17.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.17.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.17.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.18.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.18.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.18.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.18.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.19.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.19.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.19.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.19.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.2.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.2.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.2.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.2.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.20.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.20.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.20.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.20.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.21.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.21.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.21.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.21.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.22.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.22.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.22.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.22.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.23.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.23.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.23.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.23.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.24.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.24.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.24.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.24.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.25.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.25.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.25.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.25.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.26.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.26.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.26.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.26.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.27.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.27.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.27.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.27.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.28.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.28.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.28.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.28.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.29.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.29.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.29.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.29.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.3.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.3.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.3.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.3.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.30.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.30.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.30.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.30.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.31.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.31.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.31.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.31.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.32.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.32.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.32.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.32.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.33.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.33.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.33.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.33.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.34.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.34.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.34.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.34.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.35.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.35.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.35.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.35.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.36.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.36.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.36.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.36.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.37.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.37.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.37.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.37.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.38.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.38.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.38.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.38.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.39.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.39.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.39.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.39.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.4.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.4.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.4.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.4.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.40.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.40.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.40.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.40.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.41.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.41.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.41.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.41.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.42.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.42.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.42.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.42.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.43.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.43.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.43.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.43.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.44.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.44.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.44.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.44.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.45.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.45.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.45.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.45.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.46.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.46.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.46.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.46.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.47.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.47.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.47.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.47.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.48.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.48.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.48.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.48.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.49.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.49.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.49.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.49.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.5.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.5.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.5.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.5.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.50.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.50.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.50.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.50.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.51.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.51.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.51.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.51.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.52.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.52.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.52.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.52.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.53.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.53.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.53.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.53.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.54.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.54.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.54.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.54.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.55.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.55.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.55.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.55.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.56.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.56.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.56.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.56.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.57.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.57.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.57.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.57.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.58.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.58.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.58.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.58.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.59.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.59.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.59.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.59.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.6.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.6.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.6.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.6.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.60.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.60.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.60.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.60.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.61.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.61.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.61.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.61.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.62.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.62.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.62.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.62.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.63.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.63.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.63.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.63.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.64.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.64.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.64.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.64.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.65.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.65.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.65.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.65.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.66.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.66.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.66.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.66.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.67.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.67.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.67.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.67.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.68.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.68.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.68.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.68.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.69.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.69.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.69.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.69.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.7.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.7.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.7.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.7.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.70.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.70.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.70.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.70.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.71.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.71.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.71.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.71.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.72.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.72.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.72.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.72.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.73.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.73.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.73.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.73.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.74.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.74.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.74.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.74.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.75.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.75.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.75.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.75.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.76.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.76.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.76.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.76.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.77.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.77.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.77.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.77.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.78.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.78.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.78.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.78.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.79.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.79.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.79.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.79.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.8.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.8.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.8.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.8.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.80.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.80.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.80.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.80.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.81.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.81.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.81.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.81.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.82.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.82.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.82.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.82.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.83.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.83.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.83.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.83.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.84.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.84.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.84.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.84.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.85.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.85.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.85.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.85.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.86.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.86.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.86.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.86.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.87.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.87.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.87.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.87.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.88.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.88.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.88.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.88.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.89.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.89.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.89.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.89.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.9.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.9.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.9.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.9.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.90.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.90.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.90.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.90.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.91.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.91.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.91.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.91.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.92.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.92.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.92.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.92.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.93.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.93.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.93.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.93.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.94.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.94.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.94.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.94.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.95.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.95.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.95.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.95.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.96.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.96.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.96.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.96.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.97.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.97.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.97.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.97.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.98.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.98.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.98.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.98.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.99.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.99.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.99.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.26.mlp.experts.99.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.0.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.1.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.10.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.100.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.101.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.102.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.103.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.104.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.105.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.106.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.107.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.108.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.109.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.11.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.110.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.111.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.112.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.113.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.114.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.115.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.116.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.117.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.118.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.119.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.12.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.120.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.121.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.122.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.123.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.124.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.125.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.126.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.127.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.13.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.14.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.15.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.16.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.17.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.18.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.19.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.2.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.20.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.21.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.22.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.23.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.24.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.25.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.26.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.27.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.28.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.29.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.3.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.30.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.31.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.32.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.33.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.34.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.35.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.36.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.37.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.38.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.39.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.4.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.40.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.41.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.42.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.43.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.44.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.45.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.46.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.47.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.48.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.49.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.5.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.50.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.51.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.52.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.53.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.54.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.55.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.56.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.57.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.58.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.59.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.6.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.60.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.61.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.62.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.63.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.64.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.65.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.66.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.67.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.68.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.69.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.7.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.70.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.71.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.72.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.73.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.74.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.75.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.76.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.77.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.78.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.79.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.8.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.80.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.81.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.82.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.83.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.84.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.85.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.86.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.87.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.88.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.89.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.9.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.90.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.91.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.92.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.93.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.94.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.95.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.96.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.97.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.98.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.experts.99.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.gate.e_score_correction_bias": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.gate.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.shared_experts.down_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.shared_experts.gate_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00029-of-00048.safetensors",
+ "model.layers.27.mlp.shared_experts.up_proj.weight_scale": "model-00029-of-00048.safetensors",
+ "model.layers.40.mlp.experts.0.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.0.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.0.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.0.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.1.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.1.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.1.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.1.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.10.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.10.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.10.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.10.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.100.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.100.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.100.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.100.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.101.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.101.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.101.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.101.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.102.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.102.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.102.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.102.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.103.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.103.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.103.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.103.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.104.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.104.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.104.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.104.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.105.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.105.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.105.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.105.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.106.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.106.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.106.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.106.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.107.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.107.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.107.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.107.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.108.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.108.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.108.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.108.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.109.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.109.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.109.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.109.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.11.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.11.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.11.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.11.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.110.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.110.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.110.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.110.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.111.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.111.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.111.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.111.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.112.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.112.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.112.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.112.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.113.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.113.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.113.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.113.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.114.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.114.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.114.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.114.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.115.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.115.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.115.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.115.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.116.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.116.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.116.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.116.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.117.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.117.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.117.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.117.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.118.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.118.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.118.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.118.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.119.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.119.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.119.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.119.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.12.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.12.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.12.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.12.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.120.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.120.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.120.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.120.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.121.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.121.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.121.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.121.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.122.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.122.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.122.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.122.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.123.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.123.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.123.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.123.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.124.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.124.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.124.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.124.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.125.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.125.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.125.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.125.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.126.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.126.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.126.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.126.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.127.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.127.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.127.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.127.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.13.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.13.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.13.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.13.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.14.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.14.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.14.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.14.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.15.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.15.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.15.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.15.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.16.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.16.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.16.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.16.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.17.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.17.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.17.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.17.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.18.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.18.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.18.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.18.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.19.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.19.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.19.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.19.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.2.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.2.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.2.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.2.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.20.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.20.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.20.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.20.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.21.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.21.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.21.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.21.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.22.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.22.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.22.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.22.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.23.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.23.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.23.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.23.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.24.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.24.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.24.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.24.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.25.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.25.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.25.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.25.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.26.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.26.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.26.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.26.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.27.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.27.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.27.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.27.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.28.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.28.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.28.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.28.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.29.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.29.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.29.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.29.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.3.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.3.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.3.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.3.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.30.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.30.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.30.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.30.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.31.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.31.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.31.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.31.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.32.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.32.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.32.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.32.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.33.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.33.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.33.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.33.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.34.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.34.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.34.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.34.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.35.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.35.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.35.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.35.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.36.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.36.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.36.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.36.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.37.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.37.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.37.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.37.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.38.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.38.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.38.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.38.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.39.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.39.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.39.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.39.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.4.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.4.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.4.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.4.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.40.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.40.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.40.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.40.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.41.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.41.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.41.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.41.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.42.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.42.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.42.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.42.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.43.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.43.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.43.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.43.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.44.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.44.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.44.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.44.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.45.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.45.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.45.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.45.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.46.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.46.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.46.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.46.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.47.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.47.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.47.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.47.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.48.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.48.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.48.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.48.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.49.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.49.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.49.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.49.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.5.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.5.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.5.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.5.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.50.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.50.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.50.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.50.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.51.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.51.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.51.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.51.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.52.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.52.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.52.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.52.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.53.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.53.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.53.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.53.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.54.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.54.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.54.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.54.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.55.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.55.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.55.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.55.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.56.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.56.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.56.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.56.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.57.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.57.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.57.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.57.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.58.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.58.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.58.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.58.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.59.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.59.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.59.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.59.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.6.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.6.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.6.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.6.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.60.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.60.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.60.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.60.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.61.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.61.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.61.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.61.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.62.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.62.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.62.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.62.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.63.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.63.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.63.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.63.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.64.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.64.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.64.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.64.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.65.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.65.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.65.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.65.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.66.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.66.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.66.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.66.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.67.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.67.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.67.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.67.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.68.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.68.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.68.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.68.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.69.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.69.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.69.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.69.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.7.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.7.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.7.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.7.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.70.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.70.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.70.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.70.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.71.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.71.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.71.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.71.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.72.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.72.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.72.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.72.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.73.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.73.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.73.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.73.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.74.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.74.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.74.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.74.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.75.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.75.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.75.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.75.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.76.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.76.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.76.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.76.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.77.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.77.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.77.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.77.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.78.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.78.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.78.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.78.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.79.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.79.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.79.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.79.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.8.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.8.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.8.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.8.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.80.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.80.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.80.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.80.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.81.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.81.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.81.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.81.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.82.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.82.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.82.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.82.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.83.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.83.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.83.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.83.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.84.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.84.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.84.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.84.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.85.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.85.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.85.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.85.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.86.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.86.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.86.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.86.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.87.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.87.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.87.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.87.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.88.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.88.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.88.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.88.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.89.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.89.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.89.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.89.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.9.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.9.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.9.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.9.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.90.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.90.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.90.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.90.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.91.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.91.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.91.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.91.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.92.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.92.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.92.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.92.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.93.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.93.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.93.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.93.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.94.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.94.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.94.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.94.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.95.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.95.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.95.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.95.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.96.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.96.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.96.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.96.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.97.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.97.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.97.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.97.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.98.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.98.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.98.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.98.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.99.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.99.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.99.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.40.mlp.experts.99.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.0.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.1.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.10.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.100.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.100.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.101.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.101.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.102.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.102.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.103.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.103.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.104.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.104.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.105.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.105.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.106.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.106.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.107.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.107.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.108.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.108.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.109.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.109.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.11.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.110.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.110.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.111.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.111.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.112.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.112.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.113.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.113.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.114.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.114.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.115.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.115.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.116.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.116.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.117.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.117.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.118.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.118.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.119.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.119.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.12.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.120.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.120.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.121.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.121.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.122.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.122.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.123.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.123.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.124.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.124.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.125.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.125.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.126.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.126.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.127.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.127.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.13.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.14.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.15.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.16.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.17.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.18.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.19.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.2.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.20.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.21.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.22.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.23.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.24.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.25.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.26.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.27.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.28.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.29.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.3.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.30.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.31.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.32.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.33.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.34.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.35.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.36.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.37.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.38.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.39.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.4.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.40.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.41.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.42.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.43.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.44.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.45.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.46.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.47.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.48.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.49.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.5.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.50.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.51.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.52.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.53.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.54.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.55.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.56.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.57.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.58.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.59.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.6.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.60.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.61.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.62.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.63.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.64.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.64.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.65.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.65.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.66.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.66.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.67.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.67.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.68.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.68.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.69.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.69.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.7.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.70.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.70.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.71.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.71.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.72.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.72.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.73.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.73.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.74.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.74.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.75.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.75.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.76.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.76.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.77.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.77.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.78.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.78.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.79.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.79.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.8.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.80.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.80.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.81.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.81.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.82.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.82.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.83.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.83.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.84.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.84.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.85.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.85.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.86.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.86.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.87.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.87.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.88.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.88.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.89.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.89.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.9.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.90.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.90.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.91.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.91.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.92.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.92.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.93.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.93.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.94.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.94.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.95.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.95.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.96.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.96.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.97.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.97.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.98.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.98.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.99.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.experts.99.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.gate.e_score_correction_bias": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.gate.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.shared_experts.down_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.shared_experts.gate_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00043-of-00048.safetensors",
+ "model.layers.41.mlp.shared_experts.up_proj.weight_scale": "model-00043-of-00048.safetensors",
+ "model.layers.2.mlp.experts.0.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.0.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.0.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.0.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.1.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.1.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.1.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.1.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.10.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.10.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.10.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.10.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.100.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.100.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.100.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.100.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.101.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.101.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.101.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.101.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.102.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.102.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.102.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.102.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.103.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.103.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.103.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.103.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.104.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.104.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.104.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.104.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.105.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.105.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.105.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.105.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.106.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.106.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.106.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.106.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.107.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.107.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.107.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.107.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.108.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.108.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.108.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.108.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.109.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.109.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.109.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.109.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.11.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.11.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.11.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.11.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.110.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.110.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.110.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.110.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.111.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.111.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.111.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.111.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.112.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.112.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.112.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.112.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.113.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.113.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.113.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.113.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.114.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.114.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.114.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.114.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.115.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.115.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.115.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.115.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.116.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.116.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.116.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.116.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.117.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.117.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.117.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.117.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.118.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.118.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.118.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.118.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.119.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.119.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.119.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.119.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.12.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.12.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.12.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.12.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.120.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.120.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.120.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.120.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.121.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.121.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.121.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.121.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.122.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.122.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.122.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.122.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.123.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.123.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.123.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.123.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.124.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.124.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.124.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.124.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.125.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.125.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.125.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.125.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.126.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.126.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.126.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.126.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.127.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.127.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.127.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.127.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.13.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.13.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.13.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.13.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.14.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.14.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.14.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.14.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.15.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.15.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.15.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.15.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.16.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.16.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.16.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.16.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.17.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.17.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.17.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.17.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.18.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.18.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.18.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.18.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.19.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.19.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.19.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.19.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.2.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.2.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.2.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.2.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.20.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.20.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.20.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.20.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.21.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.21.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.21.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.21.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.22.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.22.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.22.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.22.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.23.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.23.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.23.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.23.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.24.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.24.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.24.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.24.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.25.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.25.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.25.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.25.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.26.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.26.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.26.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.26.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.27.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.27.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.27.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.27.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.28.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.28.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.28.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.28.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.29.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.29.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.29.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.29.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.3.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.3.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.3.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.3.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.30.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.30.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.30.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.30.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.31.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.31.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.31.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.31.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.32.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.32.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.32.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.32.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.33.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.33.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.33.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.33.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.34.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.34.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.34.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.34.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.35.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.35.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.35.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.35.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.36.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.36.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.36.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.36.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.37.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.37.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.37.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.37.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.38.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.38.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.38.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.38.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.39.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.39.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.39.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.39.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.4.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.4.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.4.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.4.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.40.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.40.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.40.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.40.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.41.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.41.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.41.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.41.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.42.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.42.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.42.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.42.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.43.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.43.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.43.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.43.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.44.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.44.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.44.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.44.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.45.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.45.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.45.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.45.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.46.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.46.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.46.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.46.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.47.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.47.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.47.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.47.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.48.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.48.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.48.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.48.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.49.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.49.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.49.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.49.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.5.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.5.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.5.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.5.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.50.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.50.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.50.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.50.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.51.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.51.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.51.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.51.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.52.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.52.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.52.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.52.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.53.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.53.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.53.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.53.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.54.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.54.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.54.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.54.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.55.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.55.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.55.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.55.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.56.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.56.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.56.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.56.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.57.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.57.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.57.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.57.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.58.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.58.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.58.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.58.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.59.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.59.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.59.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.59.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.6.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.6.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.6.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.6.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.60.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.60.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.60.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.60.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.61.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.61.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.61.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.61.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.62.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.62.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.62.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.62.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.63.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.63.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.63.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.63.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.64.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.64.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.64.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.64.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.65.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.65.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.65.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.65.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.66.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.66.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.66.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.66.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.67.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.67.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.67.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.67.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.68.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.68.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.68.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.68.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.69.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.69.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.69.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.69.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.7.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.7.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.7.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.7.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.70.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.70.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.70.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.70.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.71.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.71.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.71.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.71.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.72.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.72.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.72.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.72.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.73.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.73.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.73.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.73.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.74.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.74.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.74.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.74.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.75.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.75.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.75.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.75.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.76.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.76.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.76.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.76.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.77.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.77.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.77.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.77.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.78.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.78.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.78.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.78.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.79.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.79.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.79.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.79.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.8.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.8.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.8.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.8.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.80.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.80.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.80.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.80.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.81.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.81.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.81.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.81.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.82.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.82.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.82.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.82.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.83.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.83.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.83.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.83.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.84.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.84.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.84.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.84.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.85.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.85.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.85.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.85.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.86.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.86.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.86.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.86.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.87.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.87.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.87.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.87.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.88.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.88.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.88.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.88.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.89.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.89.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.89.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.89.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.9.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.9.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.9.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.9.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.90.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.90.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.90.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.90.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.91.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.91.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.91.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.91.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.92.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.92.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.92.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.92.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.93.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.93.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.93.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.93.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.94.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.94.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.94.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.94.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.95.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.95.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.95.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.95.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.96.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.96.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.96.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.96.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.97.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.97.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.97.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.97.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.98.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.98.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.98.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.98.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.99.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.99.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.99.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.2.mlp.experts.99.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.0.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.1.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.10.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.100.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.101.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.102.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.103.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.104.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.105.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.106.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.107.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.108.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.109.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.11.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.110.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.111.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.112.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.113.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.114.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.115.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.116.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.117.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.118.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.119.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.12.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.120.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.121.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.122.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.123.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.124.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.125.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.126.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.127.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.13.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.14.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.15.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.16.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.17.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.18.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.19.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.2.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.20.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.21.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.22.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.23.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.24.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.25.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.26.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.27.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.28.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.29.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.3.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.30.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.31.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.32.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.33.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.34.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.35.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.36.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.37.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.38.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.39.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.4.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.40.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.41.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.42.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.43.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.44.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.45.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.46.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.47.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.48.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.49.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.5.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.50.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.51.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.52.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.53.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.54.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.55.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.56.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.57.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.58.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.59.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.6.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.60.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.61.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.62.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.63.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.64.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.65.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.66.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.67.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.68.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.69.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.7.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.70.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.71.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.72.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.73.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.74.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.75.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.76.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.77.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.78.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.79.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.8.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.80.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.81.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.82.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.83.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.84.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.85.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.86.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.87.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.88.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.89.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.9.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.90.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.91.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.92.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.93.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.94.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.95.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.96.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.97.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.98.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.experts.99.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.gate.e_score_correction_bias": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.gate.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.shared_experts.down_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.shared_experts.gate_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00005-of-00048.safetensors",
+ "model.layers.3.mlp.shared_experts.up_proj.weight_scale": "model-00005-of-00048.safetensors",
+ "model.layers.38.mlp.experts.0.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.0.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.0.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.0.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.1.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.1.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.1.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.1.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.10.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.10.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.10.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.10.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.100.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.100.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.100.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.100.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.101.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.101.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.101.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.101.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.102.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.102.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.102.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.102.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.103.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.103.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.103.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.103.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.104.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.104.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.104.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.104.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.105.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.105.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.105.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.105.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.106.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.106.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.106.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.106.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.107.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.107.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.107.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.107.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.108.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.108.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.108.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.108.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.109.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.109.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.109.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.109.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.11.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.11.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.11.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.11.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.110.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.110.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.110.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.110.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.111.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.111.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.111.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.111.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.112.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.112.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.112.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.112.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.113.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.113.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.113.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.113.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.114.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.114.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.114.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.114.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.115.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.115.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.115.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.115.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.116.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.116.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.116.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.116.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.117.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.117.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.117.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.117.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.118.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.118.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.118.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.118.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.119.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.119.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.119.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.119.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.12.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.12.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.12.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.12.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.120.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.120.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.120.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.120.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.121.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.121.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.121.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.121.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.122.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.122.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.122.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.122.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.123.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.123.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.123.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.123.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.124.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.124.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.124.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.124.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.125.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.125.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.125.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.125.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.126.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.126.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.126.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.126.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.127.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.127.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.127.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.127.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.13.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.13.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.13.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.13.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.14.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.14.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.14.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.14.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.15.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.15.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.15.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.15.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.16.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.16.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.16.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.16.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.17.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.17.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.17.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.17.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.18.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.18.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.18.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.18.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.19.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.19.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.19.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.19.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.2.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.2.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.2.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.2.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.20.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.20.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.20.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.20.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.21.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.21.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.21.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.21.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.22.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.22.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.22.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.22.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.23.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.23.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.23.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.23.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.24.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.24.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.24.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.24.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.25.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.25.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.25.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.25.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.26.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.26.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.26.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.26.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.27.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.27.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.27.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.27.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.28.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.28.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.28.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.28.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.29.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.29.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.29.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.29.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.3.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.3.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.3.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.3.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.30.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.30.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.30.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.30.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.31.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.31.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.31.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.31.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.32.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.32.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.32.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.32.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.33.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.33.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.33.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.33.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.34.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.34.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.34.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.34.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.35.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.35.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.35.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.35.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.36.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.36.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.36.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.36.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.37.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.37.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.37.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.37.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.38.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.38.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.38.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.38.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.39.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.39.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.39.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.39.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.4.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.4.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.4.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.4.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.40.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.40.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.40.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.40.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.41.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.41.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.41.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.41.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.42.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.42.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.42.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.42.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.43.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.43.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.43.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.43.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.44.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.44.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.44.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.44.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.45.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.45.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.45.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.45.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.46.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.46.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.46.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.46.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.47.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.47.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.47.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.47.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.48.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.48.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.48.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.48.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.49.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.49.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.49.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.49.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.5.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.5.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.5.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.5.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.50.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.50.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.50.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.50.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.51.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.51.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.51.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.51.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.52.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.52.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.52.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.52.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.53.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.53.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.53.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.53.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.54.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.54.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.54.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.54.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.55.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.55.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.55.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.55.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.56.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.56.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.56.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.56.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.57.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.57.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.57.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.57.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.58.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.58.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.58.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.58.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.59.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.59.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.59.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.59.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.6.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.6.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.6.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.6.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.60.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.60.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.60.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.60.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.61.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.61.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.61.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.61.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.62.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.62.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.62.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.62.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.63.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.63.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.63.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.63.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.64.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.64.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.64.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.64.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.65.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.65.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.65.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.65.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.66.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.66.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.66.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.66.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.67.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.67.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.67.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.67.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.68.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.68.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.68.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.68.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.69.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.69.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.69.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.69.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.7.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.7.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.7.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.7.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.70.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.70.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.70.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.70.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.71.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.71.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.71.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.71.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.72.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.72.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.72.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.72.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.73.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.73.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.73.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.73.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.74.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.74.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.74.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.74.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.75.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.75.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.75.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.75.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.76.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.76.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.76.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.76.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.77.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.77.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.77.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.77.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.78.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.78.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.78.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.78.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.79.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.79.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.79.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.79.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.8.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.8.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.8.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.8.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.80.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.80.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.80.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.80.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.81.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.81.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.81.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.81.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.82.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.82.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.82.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.82.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.83.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.83.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.83.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.83.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.84.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.84.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.84.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.84.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.85.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.85.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.85.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.85.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.86.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.86.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.86.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.86.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.87.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.87.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.87.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.87.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.88.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.88.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.88.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.88.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.89.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.89.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.89.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.89.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.9.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.9.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.9.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.9.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.90.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.90.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.90.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.90.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.91.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.91.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.91.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.91.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.92.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.92.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.92.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.92.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.93.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.93.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.93.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.93.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.94.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.94.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.94.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.94.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.95.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.95.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.95.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.95.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.96.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.96.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.96.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.96.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.97.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.97.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.97.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.97.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.98.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.98.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.98.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.98.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.99.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.99.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.99.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.38.mlp.experts.99.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.0.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.1.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.10.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.100.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.100.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.101.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.101.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.102.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.102.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.103.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.103.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.104.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.104.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.105.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.105.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.106.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.106.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.107.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.107.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.108.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.108.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.109.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.109.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.11.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.110.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.110.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.111.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.111.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.112.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.112.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.113.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.113.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.114.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.114.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.115.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.115.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.116.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.116.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.117.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.117.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.118.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.118.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.119.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.119.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.12.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.120.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.120.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.121.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.121.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.122.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.122.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.123.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.123.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.124.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.124.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.125.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.125.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.126.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.126.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.127.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.127.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.13.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.14.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.15.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.16.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.17.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.18.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.19.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.2.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.20.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.21.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.22.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.23.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.24.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.25.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.26.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.27.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.28.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.29.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.3.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.30.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.31.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.32.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.33.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.34.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.35.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.36.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.37.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.38.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.39.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.4.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.40.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.41.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.42.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.43.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.44.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.45.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.46.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.47.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.48.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.49.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.5.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.50.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.51.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.52.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.53.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.54.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.55.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.56.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.57.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.58.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.59.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.6.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.60.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.61.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.62.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.63.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.64.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.64.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.65.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.65.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.66.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.66.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.67.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.67.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.68.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.68.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.69.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.69.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.7.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.70.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.70.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.71.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.71.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.72.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.72.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.73.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.73.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.74.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.74.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.75.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.75.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.76.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.76.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.77.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.77.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.78.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.78.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.79.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.79.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.8.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.80.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.80.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.81.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.81.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.82.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.82.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.83.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.83.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.84.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.84.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.85.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.85.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.86.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.86.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.87.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.87.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.88.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.88.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.89.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.89.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.9.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.90.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.90.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.91.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.91.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.92.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.92.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.93.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.93.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.94.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.94.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.95.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.95.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.96.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.96.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.97.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.97.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.98.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.98.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.99.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.experts.99.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.gate.e_score_correction_bias": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.gate.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.shared_experts.down_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.shared_experts.gate_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00041-of-00048.safetensors",
+ "model.layers.39.mlp.shared_experts.up_proj.weight_scale": "model-00041-of-00048.safetensors",
+ "model.layers.4.mlp.experts.0.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.0.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.0.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.0.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.1.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.1.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.1.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.1.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.10.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.10.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.10.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.10.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.100.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.100.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.100.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.100.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.101.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.101.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.101.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.101.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.102.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.102.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.102.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.102.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.103.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.103.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.103.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.103.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.104.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.104.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.104.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.104.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.105.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.105.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.105.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.105.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.106.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.106.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.106.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.106.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.107.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.107.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.107.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.107.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.108.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.108.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.108.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.108.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.109.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.109.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.109.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.109.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.11.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.11.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.11.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.11.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.110.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.110.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.110.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.110.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.111.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.111.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.111.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.111.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.112.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.112.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.112.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.112.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.113.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.113.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.113.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.113.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.114.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.114.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.114.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.114.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.115.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.115.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.115.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.115.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.116.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.116.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.116.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.116.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.117.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.117.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.117.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.117.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.118.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.118.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.118.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.118.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.119.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.119.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.119.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.119.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.12.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.12.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.12.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.12.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.120.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.120.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.120.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.120.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.121.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.121.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.121.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.121.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.122.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.122.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.122.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.122.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.123.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.123.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.123.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.123.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.124.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.124.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.124.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.124.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.125.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.125.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.125.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.125.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.126.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.126.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.126.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.126.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.127.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.127.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.127.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.127.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.13.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.13.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.13.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.13.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.14.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.14.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.14.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.14.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.15.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.15.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.15.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.15.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.16.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.16.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.16.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.16.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.17.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.17.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.17.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.17.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.18.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.18.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.18.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.18.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.19.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.19.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.19.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.19.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.2.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.2.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.2.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.2.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.20.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.20.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.20.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.20.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.21.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.21.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.21.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.21.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.22.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.22.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.22.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.22.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.23.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.23.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.23.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.23.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.24.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.24.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.24.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.24.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.25.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.25.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.25.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.25.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.26.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.26.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.26.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.26.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.27.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.27.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.27.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.27.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.28.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.28.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.28.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.28.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.29.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.29.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.29.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.29.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.3.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.3.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.3.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.3.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.30.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.30.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.30.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.30.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.31.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.31.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.31.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.31.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.32.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.32.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.32.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.32.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.33.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.33.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.33.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.33.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.34.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.34.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.34.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.34.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.35.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.35.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.35.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.35.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.36.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.36.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.36.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.36.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.37.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.37.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.37.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.37.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.38.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.38.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.38.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.38.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.39.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.39.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.39.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.39.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.4.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.4.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.4.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.4.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.40.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.40.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.40.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.40.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.41.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.41.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.41.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.41.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.42.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.42.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.42.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.42.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.43.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.43.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.43.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.43.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.44.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.44.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.44.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.44.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.45.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.45.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.45.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.45.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.46.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.46.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.46.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.46.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.47.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.47.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.47.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.47.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.48.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.48.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.48.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.48.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.49.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.49.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.49.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.49.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.5.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.5.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.5.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.5.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.50.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.50.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.50.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.50.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.51.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.51.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.51.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.51.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.52.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.52.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.52.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.52.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.53.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.53.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.53.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.53.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.54.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.54.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.54.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.54.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.55.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.55.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.55.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.55.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.56.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.56.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.56.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.56.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.57.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.57.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.57.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.57.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.58.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.58.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.58.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.58.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.59.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.59.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.59.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.59.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.6.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.6.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.6.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.6.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.60.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.60.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.60.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.60.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.61.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.61.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.61.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.61.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.62.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.62.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.62.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.62.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.63.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.63.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.63.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.63.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.64.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.64.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.64.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.64.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.65.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.65.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.65.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.65.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.66.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.66.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.66.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.66.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.67.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.67.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.67.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.67.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.68.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.68.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.68.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.68.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.69.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.69.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.69.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.69.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.7.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.7.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.7.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.7.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.70.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.70.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.70.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.70.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.71.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.71.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.71.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.71.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.72.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.72.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.72.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.72.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.73.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.73.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.73.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.73.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.74.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.74.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.74.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.74.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.75.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.75.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.75.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.75.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.76.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.76.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.76.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.76.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.77.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.77.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.77.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.77.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.78.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.78.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.78.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.78.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.79.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.79.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.79.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.79.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.8.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.8.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.8.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.8.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.80.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.80.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.80.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.80.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.81.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.81.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.81.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.81.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.82.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.82.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.82.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.82.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.83.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.83.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.83.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.83.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.84.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.84.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.84.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.84.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.85.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.85.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.85.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.85.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.86.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.86.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.86.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.86.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.87.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.87.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.87.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.87.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.88.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.88.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.88.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.88.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.89.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.89.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.89.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.89.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.9.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.9.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.9.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.9.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.90.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.90.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.90.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.90.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.91.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.91.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.91.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.91.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.92.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.92.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.92.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.92.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.93.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.93.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.93.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.93.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.94.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.94.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.94.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.94.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.95.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.95.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.95.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.95.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.96.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.96.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.96.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.96.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.97.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.97.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.97.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.97.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.98.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.98.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.98.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.98.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.99.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.99.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.99.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.4.mlp.experts.99.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.0.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.1.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.10.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.100.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.101.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.102.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.103.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.104.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.105.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.106.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.107.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.108.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.109.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.11.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.110.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.111.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.112.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.113.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.114.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.115.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.116.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.117.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.118.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.119.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.12.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.120.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.121.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.122.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.123.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.124.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.125.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.126.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.127.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.13.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.14.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.15.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.16.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.17.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.18.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.19.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.2.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.20.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.21.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.22.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.23.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.24.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.25.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.26.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.27.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.28.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.29.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.3.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.30.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.31.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.32.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.33.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.34.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.35.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.36.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.37.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.38.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.39.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.4.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.40.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.41.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.42.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.43.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.44.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.45.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.46.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.47.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.48.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.49.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.5.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.50.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.51.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.52.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.53.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.54.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.55.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.56.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.57.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.58.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.59.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.6.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.60.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.61.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.62.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.63.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.64.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.65.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.66.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.67.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.68.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.69.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.7.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.70.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.71.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.72.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.73.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.74.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.75.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.76.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.77.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.78.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.79.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.8.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.80.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.81.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.82.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.83.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.84.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.85.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.86.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.87.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.88.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.89.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.9.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.90.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.91.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.92.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.93.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.94.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.95.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.96.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.97.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.98.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.experts.99.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.gate.e_score_correction_bias": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.gate.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.shared_experts.down_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.shared_experts.gate_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00007-of-00048.safetensors",
+ "model.layers.5.mlp.shared_experts.up_proj.weight_scale": "model-00007-of-00048.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00048.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00048.safetensors",
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00048.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00048.safetensors",
+ "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00048.safetensors",
+ "model.layers.41.mlp.experts.0.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.0.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.0.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.0.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.1.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.1.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.1.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.1.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.10.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.10.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.10.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.10.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.100.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.100.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.100.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.100.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.101.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.101.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.101.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.101.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.102.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.102.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.102.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.102.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.103.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.103.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.103.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.103.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.104.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.104.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.104.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.104.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.105.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.105.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.105.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.105.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.106.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.106.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.106.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.106.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.107.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.107.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.107.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.107.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.108.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.108.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.108.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.108.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.109.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.109.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.109.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.109.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.11.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.11.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.11.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.11.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.110.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.110.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.110.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.110.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.111.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.111.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.111.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.111.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.112.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.112.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.112.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.112.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.113.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.113.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.113.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.113.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.114.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.114.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.114.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.114.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.115.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.115.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.115.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.115.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.116.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.116.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.116.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.116.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.117.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.117.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.117.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.117.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.118.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.118.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.118.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.118.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.119.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.119.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.119.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.119.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.12.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.12.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.12.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.12.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.120.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.120.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.120.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.120.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.121.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.121.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.121.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.121.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.122.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.122.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.122.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.122.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.123.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.123.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.123.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.123.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.124.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.124.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.124.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.124.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.125.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.125.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.125.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.125.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.126.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.126.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.126.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.126.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.127.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.127.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.127.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.127.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.13.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.13.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.13.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.13.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.14.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.14.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.14.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.14.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.15.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.15.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.15.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.15.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.16.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.16.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.16.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.16.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.17.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.17.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.17.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.17.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.18.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.18.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.18.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.18.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.19.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.19.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.19.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.19.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.2.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.2.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.2.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.2.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.20.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.20.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.20.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.20.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.21.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.21.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.21.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.21.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.22.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.22.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.22.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.22.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.23.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.23.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.23.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.23.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.24.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.24.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.24.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.24.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.25.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.25.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.25.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.25.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.26.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.26.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.26.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.26.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.27.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.27.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.27.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.27.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.28.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.28.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.28.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.28.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.29.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.29.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.29.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.29.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.3.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.3.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.3.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.3.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.30.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.30.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.30.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.30.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.31.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.31.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.31.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.31.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.32.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.32.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.32.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.32.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.33.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.33.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.33.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.33.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.34.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.34.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.34.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.34.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.35.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.35.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.35.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.35.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.36.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.36.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.36.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.36.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.37.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.37.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.37.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.37.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.38.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.38.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.38.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.38.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.39.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.39.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.39.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.39.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.4.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.4.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.4.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.4.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.40.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.40.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.40.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.40.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.41.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.41.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.41.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.41.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.42.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.42.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.42.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.42.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.43.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.43.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.43.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.43.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.44.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.44.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.44.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.44.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.45.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.45.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.45.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.45.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.46.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.46.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.46.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.46.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.47.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.47.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.47.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.47.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.48.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.48.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.48.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.48.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.49.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.49.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.49.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.49.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.5.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.5.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.5.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.5.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.50.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.50.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.50.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.50.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.51.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.51.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.51.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.51.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.52.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.52.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.52.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.52.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.53.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.53.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.53.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.53.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.54.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.54.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.54.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.54.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.55.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.55.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.55.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.55.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.56.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.56.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.56.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.56.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.57.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.57.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.57.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.57.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.58.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.58.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.58.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.58.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.59.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.59.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.59.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.59.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.6.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.6.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.6.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.6.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.60.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.60.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.60.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.60.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.61.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.61.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.61.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.61.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.62.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.62.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.62.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.62.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.63.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.63.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.63.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.63.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.64.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.64.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.64.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.64.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.65.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.65.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.65.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.65.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.66.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.66.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.66.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.66.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.67.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.67.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.67.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.67.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.68.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.68.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.68.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.68.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.69.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.69.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.69.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.69.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.7.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.7.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.7.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.7.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.70.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.70.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.70.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.70.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.71.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.71.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.71.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.71.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.72.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.72.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.72.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.72.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.73.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.73.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.73.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.73.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.74.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.74.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.74.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.74.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.75.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.75.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.75.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.75.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.76.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.76.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.76.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.76.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.77.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.77.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.77.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.77.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.78.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.78.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.78.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.78.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.79.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.79.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.79.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.79.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.8.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.8.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.8.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.8.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.80.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.80.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.80.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.80.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.81.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.81.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.81.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.81.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.82.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.82.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.82.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.82.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.83.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.83.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.83.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.83.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.84.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.84.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.84.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.84.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.85.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.85.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.85.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.85.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.86.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.86.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.86.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.86.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.87.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.87.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.87.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.87.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.88.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.88.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.88.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.88.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.89.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.89.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.89.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.89.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.9.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.9.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.9.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.9.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.90.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.90.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.90.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.90.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.91.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.91.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.91.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.91.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.92.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.92.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.92.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.92.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.93.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.93.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.93.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.93.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.94.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.94.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.94.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.94.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.95.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.95.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.95.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.95.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.96.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.96.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.96.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.96.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.97.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.97.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.97.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.97.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.98.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.98.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.98.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.98.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.99.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.99.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.99.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.41.mlp.experts.99.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.0.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.1.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.10.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.100.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.100.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.101.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.101.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.102.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.102.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.103.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.103.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.104.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.104.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.105.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.105.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.106.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.106.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.107.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.107.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.108.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.108.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.109.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.109.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.11.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.110.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.110.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.111.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.111.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.112.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.112.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.113.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.113.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.114.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.114.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.115.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.115.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.116.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.116.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.117.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.117.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.118.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.118.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.119.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.119.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.12.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.120.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.120.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.121.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.121.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.122.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.122.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.123.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.123.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.124.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.124.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.125.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.125.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.126.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.126.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.127.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.127.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.13.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.14.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.15.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.16.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.17.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.18.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.19.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.2.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.20.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.21.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.22.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.23.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.24.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.25.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.26.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.27.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.28.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.29.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.3.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.30.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.31.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.32.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.33.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.34.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.35.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.36.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.37.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.38.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.39.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.4.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.40.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.41.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.42.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.43.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.44.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.45.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.46.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.47.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.48.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.49.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.5.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.50.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.51.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.52.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.53.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.54.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.55.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.56.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.57.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.58.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.59.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.6.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.60.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.61.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.62.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.63.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.64.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.64.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.65.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.65.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.66.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.66.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.67.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.67.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.68.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.68.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.69.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.69.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.7.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.70.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.70.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.71.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.71.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.72.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.72.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.73.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.73.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.74.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.74.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.75.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.75.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.76.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.76.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.77.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.77.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.78.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.78.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.79.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.79.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.8.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.80.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.80.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.81.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.81.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.82.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.82.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.83.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.83.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.84.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.84.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.85.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.85.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.86.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.86.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.87.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.87.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.88.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.88.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.89.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.89.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.9.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.90.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.90.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.91.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.91.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.92.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.92.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.93.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.93.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.94.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.94.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.95.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.95.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.96.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.96.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.97.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.97.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.98.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.98.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.99.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.experts.99.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.gate.e_score_correction_bias": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.gate.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.shared_experts.down_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.shared_experts.gate_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00044-of-00048.safetensors",
+ "model.layers.42.mlp.shared_experts.up_proj.weight_scale": "model-00044-of-00048.safetensors",
+ "model.layers.27.mlp.experts.0.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.0.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.0.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.0.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.1.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.1.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.1.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.1.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.10.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.10.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.10.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.10.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.100.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.100.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.100.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.100.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.101.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.101.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.101.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.101.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.102.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.102.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.102.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.102.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.103.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.103.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.103.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.103.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.104.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.104.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.104.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.104.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.105.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.105.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.105.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.105.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.106.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.106.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.106.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.106.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.107.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.107.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.107.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.107.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.108.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.108.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.108.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.108.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.109.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.109.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.109.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.109.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.11.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.11.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.11.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.11.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.110.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.110.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.110.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.110.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.111.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.111.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.111.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.111.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.112.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.112.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.112.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.112.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.113.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.113.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.113.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.113.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.114.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.114.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.114.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.114.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.115.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.115.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.115.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.115.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.116.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.116.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.116.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.116.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.117.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.117.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.117.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.117.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.118.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.118.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.118.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.118.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.119.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.119.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.119.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.119.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.12.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.12.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.12.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.12.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.120.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.120.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.120.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.120.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.121.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.121.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.121.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.121.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.122.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.122.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.122.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.122.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.123.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.123.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.123.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.123.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.124.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.124.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.124.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.124.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.125.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.125.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.125.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.125.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.126.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.126.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.126.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.126.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.127.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.127.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.127.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.127.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.13.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.13.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.13.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.13.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.14.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.14.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.14.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.14.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.15.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.15.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.15.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.15.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.16.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.16.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.16.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.16.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.17.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.17.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.17.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.17.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.18.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.18.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.18.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.18.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.19.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.19.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.19.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.19.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.2.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.2.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.2.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.2.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.20.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.20.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.20.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.20.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.21.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.21.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.21.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.21.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.22.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.22.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.22.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.22.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.23.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.23.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.23.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.23.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.24.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.24.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.24.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.24.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.25.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.25.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.25.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.25.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.26.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.26.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.26.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.26.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.27.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.27.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.27.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.27.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.28.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.28.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.28.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.28.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.29.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.29.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.29.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.29.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.3.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.3.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.3.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.3.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.30.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.30.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.30.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.30.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.31.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.31.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.31.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.31.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.32.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.32.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.32.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.32.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.33.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.33.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.33.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.33.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.34.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.34.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.34.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.34.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.35.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.35.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.35.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.35.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.36.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.36.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.36.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.36.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.37.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.37.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.37.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.37.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.38.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.38.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.38.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.38.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.39.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.39.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.39.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.39.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.4.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.4.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.4.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.4.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.40.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.40.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.40.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.40.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.41.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.41.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.41.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.41.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.42.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.42.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.42.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.42.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.43.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.43.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.43.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.43.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.44.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.44.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.44.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.44.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.45.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.45.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.45.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.45.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.46.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.46.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.46.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.46.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.47.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.47.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.47.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.47.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.48.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.48.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.48.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.48.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.49.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.49.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.49.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.49.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.5.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.5.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.5.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.5.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.50.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.50.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.50.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.50.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.51.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.51.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.51.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.51.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.52.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.52.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.52.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.52.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.53.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.53.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.53.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.53.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.54.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.54.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.54.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.54.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.55.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.55.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.55.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.55.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.56.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.56.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.56.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.56.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.57.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.57.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.57.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.57.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.58.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.58.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.58.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.58.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.59.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.59.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.59.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.59.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.6.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.6.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.6.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.6.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.60.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.60.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.60.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.60.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.61.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.61.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.61.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.61.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.62.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.62.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.62.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.62.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.63.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.63.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.63.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.63.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.64.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.64.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.64.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.64.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.65.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.65.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.65.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.65.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.66.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.66.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.66.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.66.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.67.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.67.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.67.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.67.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.68.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.68.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.68.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.68.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.69.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.69.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.69.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.69.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.7.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.7.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.7.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.7.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.70.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.70.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.70.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.70.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.71.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.71.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.71.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.71.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.72.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.72.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.72.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.72.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.73.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.73.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.73.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.73.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.74.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.74.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.74.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.74.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.75.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.75.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.75.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.75.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.76.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.76.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.76.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.76.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.77.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.77.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.77.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.77.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.78.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.78.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.78.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.78.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.79.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.79.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.79.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.79.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.8.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.8.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.8.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.8.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.80.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.80.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.80.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.80.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.81.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.81.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.81.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.81.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.82.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.82.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.82.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.82.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.83.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.83.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.83.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.83.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.84.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.84.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.84.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.84.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.85.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.85.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.85.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.85.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.86.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.86.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.86.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.86.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.87.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.87.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.87.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.87.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.88.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.88.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.88.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.88.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.89.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.89.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.89.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.89.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.9.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.9.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.9.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.9.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.90.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.90.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.90.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.90.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.91.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.91.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.91.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.91.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.92.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.92.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.92.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.92.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.93.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.93.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.93.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.93.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.94.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.94.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.94.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.94.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.95.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.95.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.95.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.95.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.96.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.96.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.96.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.96.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.97.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.97.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.97.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.97.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.98.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.98.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.98.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.98.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.99.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.99.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.99.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.27.mlp.experts.99.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.0.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.1.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.10.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.100.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.101.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.102.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.103.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.104.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.105.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.106.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.107.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.108.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.109.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.11.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.110.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.111.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.112.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.113.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.114.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.115.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.116.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.117.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.118.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.119.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.12.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.120.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.121.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.122.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.123.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.124.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.125.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.126.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.127.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.13.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.14.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.15.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.16.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.17.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.18.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.19.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.2.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.20.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.21.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.22.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.23.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.24.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.25.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.26.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.27.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.28.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.29.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.3.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.30.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.31.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.32.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.33.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.34.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.35.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.36.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.37.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.38.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.39.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.4.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.40.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.41.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.42.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.43.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.44.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.45.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.46.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.47.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.48.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.49.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.5.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.50.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.51.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.52.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.53.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.54.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.55.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.56.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.57.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.58.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.59.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.6.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.60.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.61.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.62.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.63.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.64.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.65.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.66.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.67.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.68.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.69.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.7.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.70.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.71.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.72.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.73.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.74.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.75.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.76.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.77.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.78.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.79.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.8.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.80.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.81.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.82.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.83.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.84.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.85.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.86.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.87.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.88.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.89.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.9.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.90.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.91.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.92.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.93.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.94.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.95.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.96.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.97.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.98.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.experts.99.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.gate.e_score_correction_bias": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.gate.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.shared_experts.down_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.shared_experts.gate_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00030-of-00048.safetensors",
+ "model.layers.28.mlp.shared_experts.up_proj.weight_scale": "model-00030-of-00048.safetensors",
+ "model.layers.17.mlp.experts.0.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.0.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.0.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.0.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.1.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.1.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.1.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.1.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.10.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.10.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.10.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.10.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.100.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.100.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.100.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.100.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.101.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.101.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.101.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.101.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.102.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.102.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.102.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.102.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.103.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.103.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.103.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.103.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.104.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.104.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.104.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.104.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.105.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.105.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.105.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.105.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.106.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.106.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.106.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.106.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.107.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.107.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.107.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.107.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.108.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.108.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.108.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.108.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.109.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.109.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.109.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.109.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.11.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.11.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.11.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.11.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.110.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.110.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.110.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.110.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.111.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.111.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.111.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.111.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.112.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.112.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.112.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.112.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.113.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.113.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.113.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.113.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.114.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.114.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.114.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.114.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.115.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.115.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.115.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.115.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.116.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.116.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.116.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.116.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.117.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.117.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.117.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.117.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.118.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.118.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.118.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.118.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.119.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.119.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.119.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.119.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.12.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.12.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.12.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.12.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.120.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.120.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.120.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.120.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.121.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.121.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.121.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.121.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.122.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.122.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.122.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.122.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.123.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.123.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.123.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.123.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.124.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.124.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.124.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.124.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.125.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.125.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.125.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.125.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.126.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.126.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.126.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.126.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.127.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.127.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.127.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.127.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.13.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.13.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.13.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.13.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.14.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.14.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.14.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.14.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.15.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.15.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.15.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.15.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.16.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.16.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.16.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.16.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.17.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.17.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.17.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.17.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.18.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.18.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.18.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.18.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.19.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.19.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.19.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.19.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.2.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.2.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.2.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.2.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.20.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.20.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.20.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.20.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.21.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.21.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.21.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.21.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.22.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.22.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.22.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.22.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.23.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.23.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.23.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.23.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.24.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.24.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.24.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.24.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.25.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.25.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.25.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.25.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.26.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.26.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.26.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.26.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.27.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.27.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.27.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.27.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.28.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.28.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.28.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.28.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.29.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.29.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.29.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.29.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.3.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.3.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.3.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.3.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.30.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.30.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.30.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.30.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.31.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.31.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.31.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.31.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.32.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.32.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.32.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.32.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.33.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.33.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.33.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.33.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.34.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.34.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.34.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.34.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.35.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.35.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.35.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.35.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.36.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.36.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.36.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.36.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.37.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.37.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.37.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.37.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.38.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.38.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.38.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.38.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.39.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.39.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.39.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.39.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.4.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.4.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.4.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.4.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.40.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.40.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.40.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.40.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.41.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.41.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.41.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.41.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.42.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.42.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.42.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.42.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.43.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.43.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.43.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.43.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.44.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.44.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.44.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.44.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.45.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.45.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.45.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.45.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.46.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.46.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.46.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.46.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.47.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.47.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.47.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.47.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.48.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.48.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.48.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.48.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.49.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.49.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.49.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.49.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.5.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.5.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.5.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.5.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.50.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.50.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.50.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.50.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.51.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.51.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.51.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.51.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.52.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.52.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.52.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.52.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.53.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.53.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.53.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.53.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.54.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.54.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.54.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.54.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.55.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.55.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.55.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.55.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.56.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.56.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.56.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.56.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.57.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.57.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.57.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.57.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.58.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.58.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.58.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.58.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.59.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.59.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.59.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.59.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.6.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.6.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.6.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.6.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.60.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.60.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.60.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.60.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.61.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.61.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.61.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.61.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.62.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.62.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.62.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.62.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.63.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.63.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.63.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.63.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.64.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.64.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.64.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.64.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.65.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.65.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.65.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.65.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.66.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.66.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.66.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.66.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.67.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.67.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.67.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.67.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.68.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.68.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.68.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.68.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.69.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.69.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.69.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.69.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.7.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.7.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.7.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.7.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.70.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.70.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.70.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.70.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.71.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.71.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.71.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.71.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.72.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.72.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.72.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.72.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.73.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.73.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.73.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.73.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.74.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.74.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.74.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.74.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.75.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.75.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.75.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.75.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.76.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.76.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.76.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.76.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.77.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.77.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.77.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.77.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.78.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.78.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.78.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.78.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.79.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.79.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.79.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.79.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.8.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.8.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.8.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.8.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.80.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.80.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.80.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.80.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.81.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.81.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.81.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.81.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.82.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.82.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.82.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.82.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.83.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.83.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.83.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.83.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.84.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.84.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.84.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.84.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.85.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.85.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.85.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.85.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.86.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.86.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.86.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.86.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.87.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.87.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.87.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.87.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.88.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.88.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.88.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.88.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.89.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.89.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.89.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.89.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.9.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.9.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.9.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.9.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.90.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.90.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.90.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.90.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.91.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.91.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.91.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.91.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.92.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.92.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.92.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.92.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.93.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.93.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.93.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.93.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.94.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.94.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.94.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.94.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.95.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.95.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.95.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.95.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.96.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.96.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.96.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.96.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.97.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.97.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.97.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.97.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.98.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.98.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.98.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.98.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.99.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.99.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.99.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.17.mlp.experts.99.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.0.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.1.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.10.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.100.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.101.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.102.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.103.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.104.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.105.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.106.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.107.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.108.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.109.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.11.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.110.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.111.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.112.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.113.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.114.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.115.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.116.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.117.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.118.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.119.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.12.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.120.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.121.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.122.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.123.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.124.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.125.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.126.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.127.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.13.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.14.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.15.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.16.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.17.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.18.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.19.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.2.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.20.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.21.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.22.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.23.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.24.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.25.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.26.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.27.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.28.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.29.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.3.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.30.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.31.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.32.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.33.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.34.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.35.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.36.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.37.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.38.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.39.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.4.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.40.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.41.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.42.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.43.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.44.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.45.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.46.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.47.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.48.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.49.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.5.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.50.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.51.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.52.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.53.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.54.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.55.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.56.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.57.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.58.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.59.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.6.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.60.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.61.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.62.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.63.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.64.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.65.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.66.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.67.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.68.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.69.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.7.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.70.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.71.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.72.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.73.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.74.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.75.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.76.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.77.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.78.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.79.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.8.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.80.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.81.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.82.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.83.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.84.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.85.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.86.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.87.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.88.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.89.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.9.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.90.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.91.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.92.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.93.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.94.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.95.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.96.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.97.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.98.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.experts.99.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.gate.e_score_correction_bias": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.gate.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.shared_experts.down_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.shared_experts.gate_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00020-of-00048.safetensors",
+ "model.layers.18.mlp.shared_experts.up_proj.weight_scale": "model-00020-of-00048.safetensors",
+ "model.layers.7.mlp.experts.0.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.0.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.0.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.0.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.1.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.1.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.1.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.1.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.10.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.10.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.10.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.10.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.100.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.100.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.100.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.100.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.101.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.101.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.101.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.101.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.102.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.102.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.102.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.102.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.103.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.103.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.103.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.103.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.104.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.104.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.104.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.104.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.105.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.105.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.105.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.105.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.106.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.106.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.106.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.106.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.107.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.107.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.107.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.107.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.108.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.108.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.108.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.108.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.109.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.109.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.109.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.109.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.11.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.11.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.11.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.11.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.110.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.110.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.110.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.110.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.111.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.111.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.111.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.111.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.112.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.112.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.112.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.112.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.113.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.113.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.113.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.113.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.114.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.114.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.114.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.114.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.115.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.115.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.115.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.115.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.116.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.116.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.116.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.116.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.117.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.117.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.117.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.117.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.118.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.118.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.118.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.118.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.119.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.119.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.119.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.119.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.12.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.12.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.12.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.12.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.120.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.120.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.120.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.120.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.121.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.121.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.121.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.121.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.122.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.122.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.122.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.122.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.123.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.123.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.123.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.123.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.124.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.124.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.124.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.124.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.125.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.125.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.125.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.125.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.126.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.126.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.126.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.126.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.127.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.127.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.127.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.127.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.13.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.13.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.13.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.13.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.14.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.14.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.14.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.14.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.15.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.15.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.15.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.15.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.16.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.16.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.16.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.16.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.17.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.17.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.17.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.17.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.18.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.18.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.18.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.18.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.19.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.19.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.19.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.19.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.2.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.2.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.2.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.2.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.20.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.20.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.20.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.20.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.21.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.21.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.21.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.21.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.22.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.22.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.22.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.22.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.23.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.23.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.23.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.23.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.24.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.24.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.24.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.24.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.25.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.25.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.25.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.25.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.26.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.26.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.26.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.26.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.27.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.27.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.27.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.27.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.28.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.28.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.28.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.28.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.29.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.29.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.29.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.29.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.3.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.3.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.3.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.3.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.30.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.30.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.30.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.30.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.31.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.31.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.31.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.31.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.32.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.32.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.32.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.32.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.33.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.33.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.33.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.33.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.34.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.34.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.34.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.34.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.35.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.35.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.35.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.35.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.36.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.36.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.36.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.36.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.37.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.37.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.37.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.37.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.38.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.38.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.38.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.38.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.39.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.39.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.39.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.39.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.4.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.4.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.4.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.4.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.40.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.40.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.40.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.40.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.41.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.41.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.41.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.41.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.42.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.42.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.42.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.42.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.43.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.43.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.43.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.43.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.44.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.44.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.44.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.44.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.45.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.45.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.45.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.45.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.46.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.46.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.46.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.46.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.47.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.47.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.47.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.47.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.48.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.48.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.48.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.48.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.49.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.49.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.49.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.49.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.5.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.5.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.5.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.5.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.50.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.50.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.50.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.50.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.51.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.51.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.51.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.51.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.52.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.52.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.52.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.52.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.53.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.53.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.53.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.53.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.54.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.54.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.54.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.54.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.55.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.55.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.55.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.55.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.56.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.56.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.56.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.56.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.57.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.57.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.57.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.57.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.58.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.58.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.58.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.58.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.59.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.59.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.59.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.59.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.6.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.6.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.6.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.6.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.60.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.60.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.60.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.60.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.61.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.61.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.61.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.61.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.62.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.62.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.62.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.62.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.63.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.63.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.63.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.63.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.64.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.64.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.64.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.64.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.65.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.65.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.65.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.65.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.66.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.66.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.66.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.66.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.67.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.67.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.67.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.67.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.68.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.68.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.68.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.68.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.69.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.69.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.69.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.69.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.7.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.7.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.7.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.7.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.70.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.70.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.70.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.70.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.71.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.71.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.71.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.71.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.72.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.72.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.72.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.72.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.73.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.73.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.73.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.73.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.74.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.74.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.74.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.74.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.75.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.75.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.75.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.75.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.76.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.76.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.76.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.76.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.77.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.77.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.77.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.77.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.78.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.78.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.78.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.78.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.79.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.79.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.79.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.79.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.8.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.8.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.8.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.8.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.80.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.80.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.80.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.80.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.81.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.81.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.81.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.81.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.82.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.82.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.82.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.82.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.83.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.83.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.83.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.83.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.84.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.84.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.84.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.84.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.85.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.85.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.85.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.85.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.86.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.86.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.86.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.86.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.87.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.87.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.87.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.87.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.88.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.88.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.88.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.88.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.89.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.89.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.89.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.89.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.9.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.9.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.9.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.9.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.90.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.90.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.90.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.90.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.91.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.91.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.91.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.91.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.92.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.92.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.92.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.92.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.93.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.93.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.93.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.93.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.94.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.94.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.94.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.94.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.95.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.95.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.95.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.95.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.96.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.96.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.96.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.96.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.97.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.97.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.97.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.97.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.98.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.98.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.98.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.98.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.99.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.99.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.99.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.7.mlp.experts.99.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.0.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.1.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.10.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.100.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.101.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.102.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.103.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.104.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.105.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.106.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.107.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.108.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.109.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.11.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.110.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.111.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.112.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.113.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.114.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.115.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.116.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.117.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.118.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.119.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.12.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.120.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.121.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.122.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.123.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.124.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.125.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.126.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.127.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.13.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.14.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.15.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.16.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.17.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.18.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.19.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.2.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.20.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.21.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.22.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.23.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.24.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.25.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.26.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.27.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.28.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.29.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.3.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.30.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.31.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.32.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.33.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.34.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.35.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.36.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.37.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.38.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.39.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.4.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.40.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.41.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.42.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.43.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.44.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.45.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.46.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.47.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.48.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.49.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.5.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.50.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.51.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.52.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.53.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.54.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.55.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.56.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.57.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.58.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.59.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.6.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.60.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.61.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.62.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.63.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.64.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.65.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.66.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.67.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.68.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.69.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.7.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.70.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.71.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.72.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.73.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.74.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.75.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.76.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.77.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.78.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.79.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.8.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.80.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.81.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.82.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.83.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.84.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.85.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.86.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.87.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.88.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.89.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.9.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.90.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.91.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.92.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.93.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.94.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.95.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.96.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.97.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.98.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.experts.99.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.gate.e_score_correction_bias": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.gate.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.shared_experts.down_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.shared_experts.gate_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00010-of-00048.safetensors",
+ "model.layers.8.mlp.shared_experts.up_proj.weight_scale": "model-00010-of-00048.safetensors",
+ "model.layers.6.mlp.experts.0.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.0.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.0.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.0.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.1.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.1.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.1.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.1.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.10.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.10.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.10.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.10.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.100.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.100.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.100.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.100.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.101.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.101.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.101.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.101.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.102.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.102.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.102.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.102.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.103.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.103.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.103.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.103.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.104.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.104.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.104.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.104.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.105.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.105.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.105.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.105.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.106.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.106.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.106.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.106.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.107.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.107.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.107.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.107.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.108.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.108.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.108.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.108.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.109.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.109.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.109.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.109.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.11.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.11.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.11.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.11.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.110.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.110.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.110.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.110.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.111.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.111.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.111.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.111.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.112.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.112.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.112.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.112.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.113.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.113.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.113.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.113.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.114.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.114.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.114.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.114.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.115.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.115.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.115.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.115.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.116.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.116.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.116.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.116.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.117.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.117.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.117.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.117.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.118.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.118.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.118.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.118.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.119.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.119.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.119.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.119.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.12.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.12.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.12.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.12.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.120.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.120.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.120.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.120.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.121.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.121.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.121.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.121.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.122.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.122.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.122.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.122.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.123.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.123.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.123.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.123.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.124.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.124.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.124.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.124.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.125.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.125.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.125.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.125.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.126.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.126.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.126.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.126.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.127.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.127.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.127.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.127.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.13.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.13.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.13.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.13.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.14.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.14.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.14.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.14.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.15.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.15.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.15.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.15.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.16.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.16.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.16.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.16.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.17.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.17.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.17.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.17.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.18.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.18.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.18.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.18.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.19.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.19.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.19.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.19.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.2.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.2.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.2.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.2.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.20.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.20.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.20.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.20.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.21.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.21.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.21.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.21.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.22.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.22.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.22.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.22.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.23.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.23.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.23.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.23.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.24.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.24.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.24.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.24.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.25.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.25.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.25.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.25.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.26.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.26.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.26.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.26.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.27.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.27.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.27.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.27.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.28.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.28.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.28.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.28.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.29.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.29.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.29.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.29.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.3.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.3.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.3.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.3.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.30.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.30.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.30.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.30.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.31.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.31.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.31.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.31.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.32.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.32.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.32.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.32.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.33.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.33.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.33.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.33.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.34.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.34.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.34.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.34.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.35.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.35.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.35.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.35.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.36.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.36.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.36.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.36.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.37.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.37.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.37.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.37.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.38.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.38.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.38.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.38.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.39.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.39.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.39.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.39.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.4.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.4.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.4.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.4.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.40.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.40.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.40.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.40.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.41.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.41.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.41.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.41.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.42.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.42.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.42.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.42.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.43.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.43.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.43.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.43.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.44.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.44.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.44.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.44.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.45.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.45.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.45.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.45.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.46.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.46.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.46.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.46.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.47.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.47.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.47.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.47.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.48.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.48.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.48.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.48.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.49.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.49.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.49.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.49.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.5.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.5.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.5.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.5.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.50.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.50.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.50.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.50.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.51.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.51.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.51.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.51.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.52.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.52.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.52.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.52.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.53.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.53.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.53.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.53.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.54.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.54.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.54.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.54.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.55.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.55.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.55.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.55.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.56.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.56.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.56.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.56.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.57.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.57.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.57.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.57.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.58.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.58.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.58.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.58.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.59.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.59.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.59.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.59.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.6.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.6.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.6.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.6.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.60.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.60.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.60.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.60.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.61.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.61.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.61.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.61.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.62.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.62.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.62.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.62.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.63.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.63.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.63.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.63.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.64.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.64.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.64.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.64.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.65.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.65.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.65.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.65.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.66.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.66.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.66.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.66.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.67.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.67.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.67.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.67.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.68.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.68.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.68.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.68.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.69.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.69.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.69.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.69.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.7.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.7.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.7.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.7.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.70.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.70.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.70.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.70.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.71.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.71.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.71.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.71.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.72.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.72.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.72.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.72.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.73.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.73.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.73.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.73.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.74.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.74.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.74.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.74.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.75.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.75.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.75.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.75.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.76.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.76.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.76.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.76.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.77.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.77.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.77.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.77.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.78.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.78.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.78.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.78.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.79.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.79.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.79.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.79.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.8.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.8.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.8.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.8.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.80.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.80.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.80.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.80.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.81.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.81.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.81.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.81.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.82.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.82.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.82.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.82.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.83.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.83.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.83.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.83.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.84.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.84.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.84.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.84.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.85.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.85.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.85.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.85.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.86.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.86.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.86.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.86.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.87.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.87.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.87.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.87.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.88.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.88.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.88.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.88.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.89.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.89.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.89.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.89.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.9.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.9.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.9.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.9.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.90.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.90.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.90.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.90.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.91.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.91.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.91.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.91.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.92.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.92.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.92.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.92.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.93.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.93.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.93.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.93.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.94.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.94.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.94.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.94.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.95.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.95.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.95.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.95.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.96.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.96.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.96.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.96.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.97.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.97.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.97.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.97.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.98.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.98.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.98.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.98.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.99.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.99.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.99.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.6.mlp.experts.99.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.0.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.1.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.10.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.100.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.101.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.102.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.103.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.104.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.105.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.106.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.107.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.108.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.109.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.11.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.110.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.111.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.112.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.113.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.114.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.115.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.116.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.117.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.118.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.119.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.12.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.120.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.121.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.122.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.123.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.124.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.125.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.126.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.127.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.13.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.14.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.15.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.16.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.17.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.18.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.19.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.2.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.20.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.21.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.22.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.23.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.24.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.25.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.26.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.27.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.28.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.29.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.3.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.30.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.31.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.32.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.33.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.34.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.35.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.36.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.37.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.38.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.39.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.4.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.40.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.41.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.42.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.43.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.44.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.45.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.46.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.47.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.48.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.49.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.5.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.50.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.51.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.52.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.53.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.54.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.55.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.56.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.57.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.58.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.59.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.6.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.60.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.61.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.62.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.63.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.64.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.65.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.66.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.67.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.68.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.69.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.7.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.70.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.71.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.72.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.73.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.74.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.75.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.76.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.77.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.78.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.79.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.8.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.80.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.81.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.82.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.83.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.84.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.85.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.86.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.87.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.88.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.89.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.9.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.90.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.91.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.92.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.93.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.94.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.95.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.96.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.97.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.98.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.experts.99.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.gate.e_score_correction_bias": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.gate.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.shared_experts.down_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.shared_experts.gate_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00009-of-00048.safetensors",
+ "model.layers.7.mlp.shared_experts.up_proj.weight_scale": "model-00009-of-00048.safetensors",
+ "model.layers.22.mlp.experts.0.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.0.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.0.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.0.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.1.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.1.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.1.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.1.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.10.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.10.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.10.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.10.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.100.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.100.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.100.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.100.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.101.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.101.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.101.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.101.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.102.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.102.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.102.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.102.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.103.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.103.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.103.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.103.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.104.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.104.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.104.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.104.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.105.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.105.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.105.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.105.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.106.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.106.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.106.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.106.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.107.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.107.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.107.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.107.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.108.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.108.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.108.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.108.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.109.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.109.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.109.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.109.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.11.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.11.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.11.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.11.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.110.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.110.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.110.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.110.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.111.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.111.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.111.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.111.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.112.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.112.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.112.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.112.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.113.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.113.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.113.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.113.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.114.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.114.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.114.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.114.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.115.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.115.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.115.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.115.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.116.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.116.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.116.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.116.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.117.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.117.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.117.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.117.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.118.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.118.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.118.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.118.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.119.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.119.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.119.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.119.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.12.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.12.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.12.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.12.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.120.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.120.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.120.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.120.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.121.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.121.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.121.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.121.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.122.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.122.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.122.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.122.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.123.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.123.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.123.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.123.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.124.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.124.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.124.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.124.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.125.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.125.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.125.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.125.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.126.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.126.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.126.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.126.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.127.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.127.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.127.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.127.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.13.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.13.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.13.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.13.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.14.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.14.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.14.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.14.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.15.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.15.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.15.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.15.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.16.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.16.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.16.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.16.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.17.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.17.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.17.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.17.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.18.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.18.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.18.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.18.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.19.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.19.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.19.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.19.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.2.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.2.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.2.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.2.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.20.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.20.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.20.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.20.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.21.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.21.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.21.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.21.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.22.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.22.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.22.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.22.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.23.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.23.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.23.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.23.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.24.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.24.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.24.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.24.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.25.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.25.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.25.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.25.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.26.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.26.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.26.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.26.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.27.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.27.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.27.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.27.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.28.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.28.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.28.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.28.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.29.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.29.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.29.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.29.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.3.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.3.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.3.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.3.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.30.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.30.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.30.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.30.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.31.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.31.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.31.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.31.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.32.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.32.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.32.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.32.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.33.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.33.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.33.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.33.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.34.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.34.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.34.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.34.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.35.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.35.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.35.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.35.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.36.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.36.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.36.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.36.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.37.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.37.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.37.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.37.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.38.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.38.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.38.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.38.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.39.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.39.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.39.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.39.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.4.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.4.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.4.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.4.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.40.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.40.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.40.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.40.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.41.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.41.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.41.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.41.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.42.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.42.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.42.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.42.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.43.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.43.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.43.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.43.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.44.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.44.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.44.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.44.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.45.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.45.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.45.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.45.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.46.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.46.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.46.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.46.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.47.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.47.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.47.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.47.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.48.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.48.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.48.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.48.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.49.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.49.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.49.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.49.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.5.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.5.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.5.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.5.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.50.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.50.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.50.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.50.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.51.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.51.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.51.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.51.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.52.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.52.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.52.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.52.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.53.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.53.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.53.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.53.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.54.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.54.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.54.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.54.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.55.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.55.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.55.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.55.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.56.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.56.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.56.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.56.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.57.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.57.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.57.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.57.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.58.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.58.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.58.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.58.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.59.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.59.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.59.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.59.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.6.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.6.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.6.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.6.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.60.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.60.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.60.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.60.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.61.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.61.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.61.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.61.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.62.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.62.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.62.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.62.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.63.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.63.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.63.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.63.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.64.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.64.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.64.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.64.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.65.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.65.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.65.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.65.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.66.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.66.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.66.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.66.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.67.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.67.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.67.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.67.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.68.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.68.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.68.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.68.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.69.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.69.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.69.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.69.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.7.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.7.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.7.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.7.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.70.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.70.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.70.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.70.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.71.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.71.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.71.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.71.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.72.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.72.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.72.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.72.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.73.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.73.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.73.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.73.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.74.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.74.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.74.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.74.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.75.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.75.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.75.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.75.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.76.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.76.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.76.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.76.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.77.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.77.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.77.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.77.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.78.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.78.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.78.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.78.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.79.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.79.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.79.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.79.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.8.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.8.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.8.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.8.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.80.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.80.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.80.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.80.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.81.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.81.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.81.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.81.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.82.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.82.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.82.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.82.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.83.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.83.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.83.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.83.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.84.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.84.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.84.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.84.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.85.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.85.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.85.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.85.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.86.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.86.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.86.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.86.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.87.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.87.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.87.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.87.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.88.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.88.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.88.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.88.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.89.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.89.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.89.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.89.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.9.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.9.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.9.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.9.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.90.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.90.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.90.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.90.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.91.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.91.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.91.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.91.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.92.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.92.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.92.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.92.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.93.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.93.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.93.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.93.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.94.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.94.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.94.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.94.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.95.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.95.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.95.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.95.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.96.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.96.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.96.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.96.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.97.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.97.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.97.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.97.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.98.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.98.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.98.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.98.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.99.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.99.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.99.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.22.mlp.experts.99.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.0.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.1.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.10.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.100.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.101.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.102.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.103.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.104.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.105.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.106.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.107.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.108.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.109.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.11.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.110.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.111.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.112.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.113.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.114.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.115.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.116.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.117.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.118.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.119.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.12.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.120.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.121.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.122.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.123.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.124.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.125.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.126.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.127.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.13.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.14.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.15.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.16.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.17.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.18.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.19.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.2.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.20.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.21.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.22.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.23.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.24.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.25.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.26.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.27.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.28.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.29.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.3.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.30.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.31.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.32.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.33.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.34.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.35.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.36.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.37.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.38.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.39.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.4.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.40.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.41.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.42.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.43.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.44.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.45.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.46.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.47.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.48.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.49.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.5.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.50.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.51.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.52.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.53.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.54.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.55.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.56.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.57.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.58.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.59.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.6.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.60.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.61.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.62.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.63.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.64.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.65.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.66.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.67.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.68.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.69.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.7.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.70.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.71.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.72.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.73.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.74.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.75.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.76.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.77.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.78.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.79.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.8.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.80.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.81.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.82.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.83.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.84.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.85.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.86.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.87.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.88.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.89.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.9.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.90.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.91.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.92.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.93.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.94.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.95.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.96.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.97.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.98.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.experts.99.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.gate.e_score_correction_bias": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.gate.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.shared_experts.down_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.shared_experts.gate_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00025-of-00048.safetensors",
+ "model.layers.23.mlp.shared_experts.up_proj.weight_scale": "model-00025-of-00048.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.28.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.29.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.29.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.30.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.30.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.30.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.30.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.31.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.31.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.31.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.31.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.32.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.32.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.32.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.32.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.33.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.33.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.33.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.33.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.34.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.34.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.34.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.34.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.35.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.35.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.35.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.35.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.35.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.36.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.36.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.36.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.36.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.36.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.37.input_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00048.safetensors",
+ "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.37.self_attn.k_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.37.self_attn.o_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.37.self_attn.q_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00048.safetensors",
+ "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00048.safetensors",
+ "model.layers.37.self_attn.v_proj.weight_scale": "model-00002-of-00048.safetensors",
+ "model.layers.34.mlp.experts.0.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.0.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.0.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.0.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.1.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.1.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.1.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.1.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.10.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.10.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.10.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.10.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.100.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.100.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.100.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.100.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.101.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.101.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.101.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.101.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.102.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.102.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.102.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.102.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.103.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.103.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.103.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.103.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.104.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.104.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.104.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.104.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.105.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.105.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.105.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.105.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.106.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.106.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.106.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.106.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.107.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.107.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.107.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.107.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.108.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.108.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.108.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.108.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.109.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.109.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.109.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.109.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.11.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.11.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.11.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.11.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.110.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.110.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.110.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.110.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.111.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.111.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.111.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.111.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.112.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.112.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.112.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.112.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.113.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.113.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.113.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.113.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.114.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.114.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.114.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.114.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.115.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.115.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.115.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.115.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.116.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.116.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.116.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.116.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.117.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.117.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.117.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.117.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.118.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.118.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.118.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.118.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.119.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.119.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.119.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.119.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.12.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.12.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.12.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.12.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.120.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.120.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.120.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.120.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.121.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.121.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.121.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.121.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.122.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.122.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.122.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.122.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.123.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.123.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.123.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.123.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.124.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.124.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.124.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.124.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.125.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.125.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.125.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.125.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.126.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.126.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.126.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.126.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.127.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.127.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.127.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.127.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.13.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.13.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.13.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.13.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.14.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.14.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.14.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.14.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.15.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.15.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.15.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.15.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.16.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.16.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.16.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.16.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.17.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.17.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.17.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.17.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.18.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.18.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.18.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.18.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.19.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.19.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.19.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.19.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.2.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.2.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.2.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.2.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.20.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.20.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.20.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.20.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.21.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.21.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.21.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.21.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.22.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.22.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.22.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.22.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.23.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.23.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.23.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.23.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.24.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.24.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.24.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.24.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.25.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.25.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.25.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.25.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.26.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.26.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.26.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.26.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.27.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.27.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.27.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.27.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.28.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.28.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.28.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.28.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.29.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.29.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.29.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.29.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.3.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.3.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.3.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.3.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.30.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.30.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.30.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.30.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.31.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.31.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.31.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.31.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.32.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.32.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.32.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.32.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.33.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.33.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.33.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.33.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.34.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.34.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.34.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.34.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.35.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.35.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.35.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.35.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.36.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.36.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.36.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.36.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.37.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.37.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.37.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.37.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.38.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.38.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.38.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.38.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.39.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.39.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.39.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.39.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.4.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.4.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.4.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.4.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.40.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.40.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.40.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.40.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.41.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.41.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.41.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.41.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.42.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.42.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.42.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.42.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.43.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.43.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.43.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.43.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.44.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.44.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.44.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.44.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.45.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.45.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.45.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.45.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.46.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.46.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.46.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.46.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.47.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.47.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.47.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.47.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.48.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.48.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.48.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.48.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.49.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.49.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.49.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.49.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.5.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.5.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.5.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.5.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.50.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.50.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.50.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.50.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.51.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.51.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.51.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.51.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.52.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.52.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.52.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.52.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.53.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.53.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.53.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.53.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.54.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.54.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.54.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.54.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.55.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.55.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.55.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.55.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.56.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.56.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.56.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.56.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.57.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.57.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.57.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.57.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.58.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.58.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.58.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.58.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.59.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.59.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.59.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.59.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.6.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.6.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.6.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.6.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.60.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.60.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.60.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.60.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.61.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.61.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.61.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.61.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.62.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.62.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.62.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.62.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.63.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.63.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.63.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.63.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.64.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.64.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.64.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.64.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.65.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.65.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.65.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.65.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.66.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.66.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.66.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.66.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.67.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.67.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.67.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.67.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.68.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.68.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.68.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.68.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.69.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.69.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.69.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.69.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.7.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.7.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.7.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.7.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.70.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.70.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.70.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.70.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.71.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.71.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.71.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.71.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.72.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.72.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.72.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.72.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.73.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.73.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.73.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.73.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.74.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.74.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.74.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.74.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.75.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.75.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.75.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.75.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.76.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.76.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.76.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.76.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.77.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.77.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.77.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.77.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.78.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.78.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.78.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.78.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.79.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.79.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.79.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.79.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.8.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.8.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.8.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.8.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.80.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.80.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.80.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.80.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.81.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.81.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.81.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.81.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.82.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.82.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.82.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.82.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.83.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.83.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.83.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.83.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.84.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.84.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.84.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.84.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.85.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.85.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.85.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.85.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.86.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.86.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.86.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.86.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.87.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.87.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.87.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.87.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.88.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.88.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.88.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.88.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.89.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.89.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.89.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.89.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.9.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.9.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.9.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.9.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.90.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.90.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.90.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.90.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.91.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.91.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.91.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.91.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.92.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.92.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.92.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.92.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.93.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.93.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.93.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.93.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.94.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.94.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.94.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.94.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.95.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.95.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.95.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.95.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.96.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.96.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.96.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.96.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.97.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.97.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.97.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.97.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.98.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.98.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.98.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.98.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.99.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.99.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.99.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.34.mlp.experts.99.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.0.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.1.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.10.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.100.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.100.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.101.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.101.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.102.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.102.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.103.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.103.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.104.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.104.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.105.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.105.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.106.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.106.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.107.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.107.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.108.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.108.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.109.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.109.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.11.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.110.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.110.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.111.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.111.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.112.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.112.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.113.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.113.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.114.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.114.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.115.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.115.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.116.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.116.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.117.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.117.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.118.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.118.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.119.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.119.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.12.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.120.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.120.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.121.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.121.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.122.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.122.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.123.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.123.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.124.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.124.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.125.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.125.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.126.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.126.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.127.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.127.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.13.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.14.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.15.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.16.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.17.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.18.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.19.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.2.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.20.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.21.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.22.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.23.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.24.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.25.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.26.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.27.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.28.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.29.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.3.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.30.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.31.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.32.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.33.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.34.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.35.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.36.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.37.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.38.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.39.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.4.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.40.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.41.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.42.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.43.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.44.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.45.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.46.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.47.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.48.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.49.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.5.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.50.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.51.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.52.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.53.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.54.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.55.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.56.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.57.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.58.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.59.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.6.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.60.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.61.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.62.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.63.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.64.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.64.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.65.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.65.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.66.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.66.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.67.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.67.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.68.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.68.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.69.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.69.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.7.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.70.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.70.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.71.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.71.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.72.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.72.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.73.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.73.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.74.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.74.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.75.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.75.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.76.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.76.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.77.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.77.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.78.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.78.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.79.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.79.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.8.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.80.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.80.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.81.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.81.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.82.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.82.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.83.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.83.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.84.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.84.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.85.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.85.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.86.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.86.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.87.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.87.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.88.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.88.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.89.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.89.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.9.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.90.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.90.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.91.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.91.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.92.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.92.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.93.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.93.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.94.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.94.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.95.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.95.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.96.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.96.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.97.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.97.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.98.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.98.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.99.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.experts.99.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.gate.e_score_correction_bias": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.gate.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.shared_experts.down_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.shared_experts.gate_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00037-of-00048.safetensors",
+ "model.layers.35.mlp.shared_experts.up_proj.weight_scale": "model-00037-of-00048.safetensors",
+ "model.layers.39.mlp.experts.0.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.0.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.0.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.0.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.1.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.1.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.1.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.1.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.10.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.10.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.10.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.10.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.100.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.100.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.100.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.100.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.101.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.101.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.101.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.101.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.102.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.102.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.102.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.102.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.103.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.103.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.103.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.103.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.104.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.104.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.104.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.104.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.105.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.105.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.105.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.105.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.106.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.106.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.106.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.106.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.107.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.107.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.107.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.107.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.108.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.108.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.108.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.108.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.109.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.109.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.109.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.109.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.11.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.11.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.11.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.11.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.110.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.110.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.110.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.110.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.111.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.111.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.111.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.111.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.112.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.112.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.112.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.112.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.113.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.113.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.113.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.113.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.114.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.114.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.114.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.114.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.115.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.115.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.115.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.115.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.116.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.116.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.116.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.116.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.117.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.117.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.117.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.117.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.118.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.118.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.118.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.118.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.119.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.119.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.119.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.119.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.12.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.12.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.12.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.12.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.120.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.120.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.120.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.120.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.121.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.121.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.121.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.121.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.122.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.122.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.122.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.122.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.123.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.123.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.123.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.123.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.124.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.124.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.124.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.124.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.125.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.125.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.125.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.125.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.126.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.126.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.126.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.126.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.127.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.127.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.127.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.127.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.13.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.13.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.13.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.13.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.14.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.14.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.14.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.14.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.15.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.15.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.15.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.15.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.16.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.16.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.16.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.16.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.17.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.17.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.17.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.17.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.18.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.18.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.18.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.18.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.19.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.19.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.19.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.19.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.2.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.2.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.2.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.2.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.20.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.20.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.20.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.20.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.21.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.21.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.21.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.21.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.22.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.22.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.22.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.22.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.23.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.23.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.23.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.23.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.24.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.24.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.24.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.24.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.25.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.25.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.25.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.25.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.26.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.26.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.26.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.26.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.27.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.27.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.27.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.27.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.28.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.28.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.28.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.28.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.29.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.29.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.29.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.29.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.3.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.3.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.3.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.3.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.30.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.30.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.30.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.30.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.31.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.31.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.31.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.31.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.32.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.32.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.32.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.32.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.33.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.33.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.33.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.33.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.34.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.34.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.34.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.34.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.35.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.35.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.35.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.35.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.36.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.36.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.36.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.36.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.37.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.37.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.37.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.37.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.38.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.38.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.38.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.38.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.39.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.39.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.39.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.39.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.4.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.4.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.4.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.4.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.40.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.40.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.40.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.40.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.41.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.41.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.41.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.41.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.42.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.42.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.42.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.42.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.43.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.43.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.43.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.43.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.44.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.44.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.44.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.44.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.45.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.45.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.45.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.45.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.46.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.46.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.46.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.46.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.47.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.47.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.47.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.47.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.48.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.48.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.48.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.48.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.49.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.49.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.49.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.49.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.5.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.5.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.5.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.5.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.50.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.50.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.50.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.50.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.51.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.51.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.51.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.51.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.52.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.52.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.52.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.52.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.53.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.53.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.53.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.53.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.54.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.54.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.54.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.54.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.55.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.55.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.55.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.55.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.56.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.56.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.56.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.56.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.57.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.57.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.57.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.57.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.58.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.58.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.58.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.58.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.59.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.59.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.59.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.59.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.6.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.6.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.6.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.6.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.60.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.60.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.60.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.60.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.61.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.61.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.61.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.61.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.62.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.62.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.62.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.62.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.63.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.63.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.63.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.63.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.64.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.64.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.64.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.64.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.65.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.65.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.65.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.65.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.66.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.66.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.66.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.66.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.67.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.67.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.67.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.67.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.68.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.68.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.68.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.68.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.69.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.69.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.69.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.69.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.7.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.7.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.7.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.7.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.70.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.70.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.70.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.70.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.71.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.71.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.71.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.71.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.72.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.72.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.72.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.72.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.73.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.73.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.73.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.73.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.74.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.74.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.74.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.74.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.75.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.75.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.75.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.75.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.76.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.76.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.76.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.76.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.77.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.77.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.77.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.77.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.78.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.78.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.78.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.78.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.79.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.79.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.79.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.79.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.8.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.8.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.8.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.8.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.80.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.80.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.80.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.80.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.81.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.81.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.81.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.81.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.82.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.82.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.82.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.82.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.83.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.83.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.83.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.83.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.84.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.84.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.84.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.84.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.85.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.85.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.85.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.85.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.86.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.86.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.86.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.86.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.87.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.87.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.87.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.87.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.88.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.88.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.88.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.88.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.89.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.89.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.89.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.89.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.9.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.9.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.9.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.9.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.90.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.90.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.90.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.90.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.91.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.91.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.91.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.91.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.92.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.92.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.92.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.92.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.93.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.93.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.93.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.93.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.94.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.94.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.94.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.94.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.95.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.95.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.95.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.95.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.96.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.96.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.96.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.96.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.97.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.97.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.97.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.97.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.98.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.98.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.98.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.98.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.99.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.99.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.99.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.39.mlp.experts.99.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.0.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.1.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.10.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.100.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.100.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.101.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.101.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.102.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.102.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.103.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.103.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.104.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.104.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.105.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.105.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.106.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.106.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.107.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.107.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.108.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.108.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.109.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.109.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.11.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.110.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.110.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.111.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.111.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.112.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.112.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.113.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.113.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.114.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.114.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.115.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.115.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.116.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.116.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.117.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.117.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.118.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.118.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.119.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.119.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.12.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.120.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.120.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.121.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.121.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.122.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.122.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.123.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.123.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.124.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.124.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.125.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.125.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.126.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.126.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.127.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.127.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.13.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.14.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.15.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.16.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.17.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.18.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.19.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.2.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.20.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.21.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.22.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.23.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.24.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.25.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.26.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.27.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.28.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.29.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.3.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.30.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.31.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.32.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.33.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.34.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.35.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.36.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.37.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.38.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.39.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.4.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.40.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.41.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.42.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.43.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.44.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.45.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.46.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.47.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.48.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.49.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.5.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.50.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.51.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.52.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.53.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.54.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.55.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.56.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.57.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.58.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.59.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.6.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.60.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.61.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.62.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.63.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.64.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.64.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.65.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.65.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.66.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.66.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.67.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.67.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.68.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.68.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.69.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.69.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.7.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.70.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.70.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.71.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.71.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.72.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.72.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.73.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.73.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.74.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.74.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.75.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.75.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.76.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.76.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.77.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.77.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.78.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.78.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.79.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.79.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.8.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.80.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.80.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.81.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.81.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.82.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.82.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.83.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.83.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.84.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.84.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.85.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.85.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.86.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.86.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.87.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.87.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.88.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.88.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.89.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.89.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.9.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.90.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.90.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.91.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.91.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.92.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.92.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.93.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.93.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.94.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.94.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.95.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.95.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.96.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.96.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.97.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.97.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.98.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.98.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.99.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.experts.99.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.gate.e_score_correction_bias": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.gate.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.shared_experts.down_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.shared_experts.gate_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00042-of-00048.safetensors",
+ "model.layers.40.mlp.shared_experts.up_proj.weight_scale": "model-00042-of-00048.safetensors",
+ "model.layers.24.mlp.experts.0.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.0.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.0.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.0.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.1.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.1.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.1.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.1.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.10.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.10.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.10.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.10.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.100.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.100.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.100.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.100.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.101.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.101.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.101.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.101.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.102.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.102.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.102.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.102.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.103.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.103.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.103.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.103.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.104.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.104.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.104.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.104.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.105.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.105.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.105.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.105.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.106.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.106.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.106.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.106.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.107.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.107.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.107.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.107.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.108.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.108.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.108.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.108.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.109.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.109.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.109.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.109.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.11.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.11.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.11.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.11.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.110.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.110.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.110.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.110.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.111.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.111.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.111.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.111.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.112.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.112.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.112.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.112.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.113.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.113.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.113.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.113.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.114.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.114.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.114.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.114.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.115.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.115.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.115.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.115.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.116.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.116.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.116.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.116.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.117.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.117.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.117.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.117.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.118.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.118.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.118.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.118.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.119.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.119.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.119.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.119.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.12.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.12.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.12.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.12.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.120.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.120.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.120.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.120.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.121.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.121.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.121.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.121.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.122.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.122.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.122.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.122.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.123.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.123.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.123.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.123.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.124.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.124.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.124.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.124.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.125.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.125.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.125.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.125.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.126.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.126.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.126.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.126.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.127.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.127.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.127.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.127.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.13.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.13.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.13.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.13.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.14.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.14.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.14.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.14.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.15.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.15.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.15.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.15.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.16.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.16.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.16.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.16.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.17.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.17.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.17.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.17.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.18.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.18.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.18.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.18.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.19.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.19.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.19.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.19.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.2.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.2.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.2.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.2.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.20.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.20.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.20.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.20.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.21.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.21.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.21.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.21.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.22.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.22.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.22.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.22.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.23.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.23.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.23.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.23.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.24.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.24.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.24.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.24.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.25.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.25.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.25.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.25.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.26.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.26.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.26.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.26.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.27.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.27.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.27.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.27.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.28.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.28.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.28.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.28.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.29.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.29.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.29.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.29.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.3.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.3.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.3.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.3.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.30.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.30.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.30.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.30.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.31.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.31.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.31.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.31.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.32.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.32.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.32.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.32.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.33.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.33.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.33.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.33.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.34.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.34.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.34.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.34.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.35.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.35.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.35.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.35.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.36.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.36.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.36.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.36.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.37.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.37.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.37.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.37.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.38.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.38.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.38.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.38.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.39.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.39.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.39.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.39.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.4.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.4.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.4.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.4.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.40.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.40.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.40.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.40.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.41.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.41.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.41.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.41.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.42.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.42.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.42.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.42.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.43.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.43.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.43.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.43.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.44.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.44.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.44.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.44.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.45.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.45.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.45.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.45.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.46.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.46.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.46.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.46.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.47.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.47.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.47.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.47.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.48.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.48.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.48.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.48.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.49.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.49.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.49.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.49.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.5.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.5.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.5.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.5.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.50.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.50.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.50.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.50.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.51.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.51.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.51.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.51.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.52.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.52.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.52.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.52.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.53.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.53.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.53.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.53.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.54.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.54.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.54.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.54.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.55.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.55.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.55.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.55.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.56.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.56.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.56.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.56.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.57.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.57.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.57.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.57.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.58.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.58.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.58.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.58.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.59.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.59.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.59.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.59.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.6.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.6.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.6.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.6.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.60.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.60.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.60.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.60.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.61.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.61.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.61.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.61.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.62.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.62.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.62.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.62.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.63.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.63.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.63.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.63.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.64.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.64.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.64.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.64.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.65.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.65.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.65.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.65.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.66.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.66.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.66.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.66.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.67.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.67.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.67.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.67.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.68.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.68.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.68.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.68.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.69.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.69.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.69.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.69.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.7.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.7.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.7.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.7.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.70.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.70.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.70.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.70.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.71.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.71.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.71.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.71.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.72.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.72.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.72.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.72.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.73.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.73.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.73.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.73.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.74.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.74.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.74.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.74.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.75.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.75.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.75.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.75.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.76.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.76.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.76.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.76.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.77.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.77.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.77.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.77.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.78.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.78.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.78.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.78.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.79.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.79.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.79.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.79.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.8.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.8.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.8.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.8.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.80.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.80.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.80.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.80.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.81.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.81.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.81.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.81.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.82.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.82.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.82.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.82.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.83.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.83.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.83.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.83.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.84.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.84.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.84.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.84.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.85.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.85.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.85.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.85.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.86.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.86.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.86.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.86.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.87.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.87.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.87.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.87.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.88.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.88.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.88.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.88.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.89.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.89.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.89.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.89.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.9.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.9.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.9.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.9.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.90.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.90.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.90.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.90.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.91.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.91.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.91.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.91.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.92.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.92.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.92.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.92.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.93.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.93.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.93.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.93.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.94.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.94.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.94.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.94.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.95.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.95.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.95.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.95.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.96.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.96.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.96.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.96.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.97.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.97.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.97.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.97.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.98.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.98.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.98.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.98.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.99.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.99.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.99.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.24.mlp.experts.99.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.0.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.1.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.10.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.100.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.101.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.102.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.103.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.104.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.105.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.106.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.107.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.108.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.109.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.11.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.110.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.111.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.112.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.113.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.114.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.115.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.116.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.117.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.118.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.119.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.12.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.120.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.121.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.122.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.123.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.124.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.125.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.126.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.127.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.13.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.14.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.15.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.16.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.17.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.18.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.19.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.2.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.20.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.21.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.22.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.23.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.24.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.25.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.26.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.27.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.28.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.29.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.3.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.30.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.31.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.32.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.33.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.34.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.35.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.36.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.37.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.38.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.39.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.4.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.40.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.41.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.42.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.43.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.44.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.45.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.46.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.47.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.48.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.49.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.5.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.50.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.51.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.52.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.53.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.54.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.55.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.56.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.57.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.58.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.59.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.6.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.60.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.61.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.62.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.63.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.64.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.65.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.66.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.67.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.68.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.69.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.7.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.70.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.71.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.72.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.73.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.74.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.75.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.76.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.77.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.78.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.79.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.8.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.80.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.81.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.82.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.83.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.84.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.85.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.86.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.87.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.88.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.89.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.9.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.90.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.91.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.92.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.93.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.94.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.95.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.96.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.97.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.98.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.experts.99.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.gate.e_score_correction_bias": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.gate.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.shared_experts.down_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.shared_experts.gate_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00027-of-00048.safetensors",
+ "model.layers.25.mlp.shared_experts.up_proj.weight_scale": "model-00027-of-00048.safetensors",
+ "model.layers.18.mlp.experts.0.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.0.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.0.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.0.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.1.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.1.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.1.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.1.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.10.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.10.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.10.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.10.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.100.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.100.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.100.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.100.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.101.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.101.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.101.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.101.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.102.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.102.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.102.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.102.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.103.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.103.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.103.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.103.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.104.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.104.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.104.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.104.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.105.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.105.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.105.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.105.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.106.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.106.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.106.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.106.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.107.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.107.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.107.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.107.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.108.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.108.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.108.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.108.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.109.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.109.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.109.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.109.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.11.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.11.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.11.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.11.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.110.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.110.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.110.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.110.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.111.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.111.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.111.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.111.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.112.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.112.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.112.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.112.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.113.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.113.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.113.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.113.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.114.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.114.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.114.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.114.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.115.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.115.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.115.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.115.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.116.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.116.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.116.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.116.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.117.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.117.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.117.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.117.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.118.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.118.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.118.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.118.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.119.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.119.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.119.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.119.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.12.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.12.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.12.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.12.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.120.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.120.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.120.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.120.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.121.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.121.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.121.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.121.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.122.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.122.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.122.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.122.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.123.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.123.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.123.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.123.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.124.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.124.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.124.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.124.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.125.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.125.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.125.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.125.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.126.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.126.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.126.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.126.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.127.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.127.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.127.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.127.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.13.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.13.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.13.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.13.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.14.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.14.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.14.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.14.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.15.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.15.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.15.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.15.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.16.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.16.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.16.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.16.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.17.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.17.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.17.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.17.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.18.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.18.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.18.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.18.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.19.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.19.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.19.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.19.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.2.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.2.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.2.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.2.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.20.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.20.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.20.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.20.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.21.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.21.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.21.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.21.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.22.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.22.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.22.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.22.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.23.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.23.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.23.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.23.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.24.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.24.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.24.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.24.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.25.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.25.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.25.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.25.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.26.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.26.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.26.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.26.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.27.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.27.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.27.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.27.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.28.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.28.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.28.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.28.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.29.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.29.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.29.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.29.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.3.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.3.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.3.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.3.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.30.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.30.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.30.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.30.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.31.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.31.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.31.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.31.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.32.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.32.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.32.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.32.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.33.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.33.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.33.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.33.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.34.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.34.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.34.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.34.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.35.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.35.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.35.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.35.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.36.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.36.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.36.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.36.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.37.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.37.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.37.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.37.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.38.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.38.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.38.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.38.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.39.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.39.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.39.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.39.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.4.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.4.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.4.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.4.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.40.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.40.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.40.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.40.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.41.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.41.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.41.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.41.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.42.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.42.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.42.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.42.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.43.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.43.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.43.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.43.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.44.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.44.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.44.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.44.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.45.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.45.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.45.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.45.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.46.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.46.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.46.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.46.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.47.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.47.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.47.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.47.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.48.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.48.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.48.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.48.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.49.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.49.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.49.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.49.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.5.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.5.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.5.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.5.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.50.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.50.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.50.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.50.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.51.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.51.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.51.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.51.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.52.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.52.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.52.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.52.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.53.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.53.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.53.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.53.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.54.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.54.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.54.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.54.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.55.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.55.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.55.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.55.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.56.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.56.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.56.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.56.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.57.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.57.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.57.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.57.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.58.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.58.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.58.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.58.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.59.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.59.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.59.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.59.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.6.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.6.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.6.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.6.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.60.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.60.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.60.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.60.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.61.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.61.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.61.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.61.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.62.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.62.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.62.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.62.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.63.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.63.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.63.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.63.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.64.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.64.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.64.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.64.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.65.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.65.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.65.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.65.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.66.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.66.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.66.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.66.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.67.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.67.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.67.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.67.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.68.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.68.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.68.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.68.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.69.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.69.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.69.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.69.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.7.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.7.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.7.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.7.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.70.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.70.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.70.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.70.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.71.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.71.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.71.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.71.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.72.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.72.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.72.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.72.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.73.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.73.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.73.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.73.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.74.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.74.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.74.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.74.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.75.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.75.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.75.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.75.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.76.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.76.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.76.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.76.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.77.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.77.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.77.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.77.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.78.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.78.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.78.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.78.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.79.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.79.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.79.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.79.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.8.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.8.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.8.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.8.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.80.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.80.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.80.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.80.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.81.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.81.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.81.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.81.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.82.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.82.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.82.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.82.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.83.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.83.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.83.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.83.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.84.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.84.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.84.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.84.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.85.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.85.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.85.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.85.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.86.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.86.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.86.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.86.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.87.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.87.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.87.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.87.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.88.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.88.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.88.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.88.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.89.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.89.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.89.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.89.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.9.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.9.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.9.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.9.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.90.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.90.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.90.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.90.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.91.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.91.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.91.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.91.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.92.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.92.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.92.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.92.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.93.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.93.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.93.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.93.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.94.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.94.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.94.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.94.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.95.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.95.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.95.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.95.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.96.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.96.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.96.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.96.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.97.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.97.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.97.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.97.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.98.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.98.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.98.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.98.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.99.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.99.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.99.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.18.mlp.experts.99.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.0.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.1.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.10.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.100.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.101.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.102.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.103.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.104.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.105.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.106.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.107.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.108.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.109.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.11.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.110.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.111.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.112.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.113.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.114.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.115.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.116.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.117.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.118.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.119.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.12.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.120.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.121.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.122.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.123.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.124.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.125.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.126.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.127.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.13.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.14.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.15.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.16.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.17.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.18.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.19.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.2.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.20.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.21.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.22.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.23.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.24.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.25.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.26.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.27.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.28.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.29.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.3.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.30.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.31.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.32.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.33.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.34.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.35.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.36.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.37.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.38.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.39.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.4.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.40.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.41.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.42.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.43.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.44.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.45.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.46.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.47.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.48.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.49.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.5.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.50.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.51.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.52.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.53.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.54.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.55.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.56.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.57.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.58.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.59.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.6.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.60.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.61.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.62.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.63.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.64.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.65.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.66.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.67.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.68.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.69.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.7.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.70.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.71.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.72.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.73.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.74.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.75.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.76.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.77.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.78.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.79.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.8.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.80.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.81.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.82.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.83.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.84.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.85.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.86.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.87.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.88.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.89.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.9.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.90.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.91.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.92.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.93.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.94.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.95.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.96.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.97.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.98.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.experts.99.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.gate.e_score_correction_bias": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.gate.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.shared_experts.down_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.shared_experts.gate_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00021-of-00048.safetensors",
+ "model.layers.19.mlp.shared_experts.up_proj.weight_scale": "model-00021-of-00048.safetensors",
+ "model.layers.36.mlp.experts.0.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.0.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.0.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.0.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.1.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.1.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.1.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.1.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.10.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.10.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.10.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.10.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.100.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.100.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.100.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.100.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.101.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.101.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.101.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.101.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.102.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.102.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.102.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.102.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.103.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.103.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.103.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.103.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.104.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.104.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.104.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.104.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.105.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.105.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.105.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.105.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.106.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.106.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.106.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.106.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.107.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.107.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.107.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.107.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.108.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.108.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.108.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.108.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.109.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.109.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.109.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.109.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.11.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.11.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.11.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.11.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.110.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.110.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.110.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.110.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.111.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.111.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.111.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.111.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.112.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.112.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.112.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.112.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.113.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.113.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.113.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.113.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.114.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.114.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.114.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.114.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.115.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.115.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.115.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.115.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.116.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.116.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.116.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.116.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.117.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.117.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.117.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.117.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.118.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.118.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.118.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.118.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.119.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.119.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.119.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.119.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.12.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.12.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.12.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.12.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.120.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.120.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.120.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.120.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.121.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.121.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.121.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.121.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.122.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.122.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.122.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.122.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.123.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.123.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.123.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.123.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.124.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.124.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.124.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.124.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.125.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.125.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.125.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.125.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.126.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.126.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.126.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.126.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.127.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.127.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.127.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.127.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.13.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.13.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.13.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.13.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.14.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.14.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.14.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.14.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.15.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.15.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.15.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.15.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.16.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.16.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.16.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.16.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.17.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.17.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.17.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.17.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.18.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.18.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.18.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.18.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.19.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.19.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.19.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.19.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.2.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.2.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.2.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.2.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.20.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.20.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.20.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.20.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.21.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.21.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.21.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.21.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.22.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.22.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.22.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.22.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.23.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.23.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.23.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.23.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.24.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.24.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.24.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.24.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.25.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.25.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.25.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.25.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.26.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.26.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.26.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.26.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.27.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.27.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.27.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.27.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.28.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.28.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.28.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.28.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.29.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.29.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.29.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.29.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.3.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.3.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.3.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.3.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.30.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.30.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.30.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.30.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.31.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.31.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.31.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.31.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.32.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.32.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.32.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.32.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.33.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.33.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.33.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.33.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.34.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.34.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.34.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.34.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.35.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.35.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.35.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.35.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.36.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.36.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.36.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.36.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.37.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.37.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.37.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.37.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.38.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.38.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.38.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.38.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.39.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.39.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.39.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.39.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.4.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.4.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.4.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.4.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.40.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.40.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.40.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.40.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.41.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.41.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.41.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.41.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.42.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.42.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.42.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.42.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.43.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.43.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.43.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.43.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.44.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.44.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.44.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.44.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.45.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.45.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.45.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.45.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.46.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.46.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.46.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.46.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.47.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.47.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.47.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.47.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.48.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.48.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.48.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.48.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.49.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.49.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.49.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.49.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.5.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.5.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.5.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.5.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.50.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.50.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.50.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.50.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.51.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.51.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.51.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.51.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.52.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.52.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.52.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.52.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.53.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.53.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.53.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.53.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.54.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.54.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.54.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.54.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.55.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.55.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.55.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.55.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.56.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.56.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.56.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.56.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.57.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.57.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.57.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.57.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.58.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.58.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.58.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.58.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.59.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.59.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.59.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.59.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.6.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.6.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.6.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.6.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.60.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.60.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.60.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.60.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.61.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.61.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.61.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.61.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.62.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.62.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.62.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.62.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.63.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.63.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.63.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.63.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.64.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.64.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.64.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.64.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.65.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.65.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.65.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.65.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.66.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.66.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.66.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.66.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.67.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.67.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.67.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.67.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.68.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.68.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.68.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.68.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.69.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.69.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.69.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.69.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.7.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.7.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.7.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.7.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.70.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.70.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.70.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.70.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.71.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.71.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.71.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.71.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.72.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.72.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.72.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.72.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.73.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.73.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.73.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.73.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.74.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.74.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.74.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.74.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.75.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.75.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.75.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.75.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.76.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.76.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.76.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.76.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.77.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.77.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.77.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.77.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.78.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.78.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.78.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.78.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.79.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.79.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.79.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.79.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.8.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.8.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.8.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.8.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.80.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.80.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.80.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.80.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.81.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.81.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.81.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.81.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.82.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.82.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.82.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.82.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.83.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.83.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.83.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.83.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.84.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.84.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.84.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.84.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.85.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.85.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.85.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.85.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.86.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.86.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.86.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.86.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.87.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.87.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.87.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.87.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.88.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.88.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.88.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.88.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.89.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.89.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.89.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.89.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.9.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.9.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.9.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.9.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.90.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.90.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.90.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.90.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.91.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.91.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.91.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.91.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.92.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.92.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.92.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.92.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.93.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.93.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.93.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.93.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.94.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.94.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.94.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.94.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.95.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.95.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.95.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.95.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.96.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.96.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.96.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.96.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.97.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.97.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.97.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.97.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.98.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.98.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.98.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.98.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.99.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.99.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.99.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.36.mlp.experts.99.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.0.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.1.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.10.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.100.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.100.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.101.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.101.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.102.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.102.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.103.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.103.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.104.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.104.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.105.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.105.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.106.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.106.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.107.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.107.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.108.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.108.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.109.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.109.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.11.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.110.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.110.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.111.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.111.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.112.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.112.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.113.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.113.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.114.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.114.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.115.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.115.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.116.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.116.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.117.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.117.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.118.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.118.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.119.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.119.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.12.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.120.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.120.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.121.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.121.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.122.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.122.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.123.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.123.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.124.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.124.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.125.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.125.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.126.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.126.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.127.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.127.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.13.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.14.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.15.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.16.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.17.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.18.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.19.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.2.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.20.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.21.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.22.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.23.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.24.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.25.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.26.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.27.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.28.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.29.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.3.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.30.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.31.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.32.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.33.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.34.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.35.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.36.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.37.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.38.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.39.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.4.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.40.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.41.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.42.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.43.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.44.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.45.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.46.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.47.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.48.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.49.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.5.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.50.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.51.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.52.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.53.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.54.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.55.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.56.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.57.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.58.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.59.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.6.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.60.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.61.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.62.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.63.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.64.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.64.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.65.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.65.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.66.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.66.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.67.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.67.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.68.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.68.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.69.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.69.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.7.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.70.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.70.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.71.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.71.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.72.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.72.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.73.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.73.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.74.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.74.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.75.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.75.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.76.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.76.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.77.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.77.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.78.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.78.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.79.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.79.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.8.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.80.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.80.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.81.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.81.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.82.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.82.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.83.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.83.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.84.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.84.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.85.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.85.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.86.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.86.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.87.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.87.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.88.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.88.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.89.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.89.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.9.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.90.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.90.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.91.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.91.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.92.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.92.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.93.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.93.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.94.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.94.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.95.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.95.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.96.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.96.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.97.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.97.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.98.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.98.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.99.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.experts.99.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.gate.e_score_correction_bias": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.gate.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.shared_experts.down_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.shared_experts.gate_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00039-of-00048.safetensors",
+ "model.layers.37.mlp.shared_experts.up_proj.weight_scale": "model-00039-of-00048.safetensors",
+ "model.layers.8.mlp.experts.0.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.0.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.0.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.0.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.1.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.1.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.1.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.1.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.10.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.10.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.10.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.10.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.100.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.100.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.100.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.100.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.101.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.101.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.101.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.101.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.102.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.102.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.102.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.102.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.103.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.103.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.103.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.103.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.104.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.104.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.104.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.104.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.105.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.105.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.105.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.105.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.106.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.106.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.106.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.106.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.107.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.107.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.107.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.107.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.108.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.108.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.108.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.108.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.109.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.109.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.109.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.109.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.11.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.11.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.11.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.11.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.110.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.110.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.110.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.110.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.111.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.111.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.111.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.111.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.112.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.112.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.112.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.112.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.113.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.113.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.113.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.113.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.114.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.114.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.114.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.114.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.115.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.115.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.115.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.115.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.116.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.116.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.116.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.116.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.117.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.117.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.117.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.117.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.118.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.118.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.118.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.118.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.119.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.119.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.119.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.119.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.12.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.12.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.12.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.12.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.120.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.120.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.120.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.120.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.121.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.121.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.121.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.121.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.122.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.122.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.122.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.122.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.123.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.123.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.123.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.123.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.124.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.124.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.124.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.124.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.125.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.125.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.125.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.125.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.126.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.126.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.126.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.126.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.127.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.127.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.127.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.127.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.13.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.13.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.13.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.13.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.14.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.14.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.14.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.14.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.15.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.15.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.15.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.15.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.16.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.16.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.16.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.16.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.17.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.17.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.17.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.17.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.18.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.18.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.18.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.18.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.19.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.19.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.19.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.19.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.2.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.2.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.2.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.2.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.20.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.20.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.20.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.20.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.21.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.21.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.21.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.21.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.22.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.22.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.22.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.22.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.23.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.23.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.23.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.23.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.24.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.24.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.24.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.24.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.25.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.25.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.25.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.25.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.26.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.26.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.26.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.26.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.27.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.27.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.27.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.27.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.28.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.28.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.28.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.28.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.29.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.29.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.29.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.29.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.3.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.3.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.3.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.3.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.30.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.30.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.30.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.30.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.31.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.31.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.31.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.31.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.32.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.32.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.32.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.32.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.33.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.33.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.33.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.33.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.34.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.34.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.34.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.34.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.35.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.35.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.35.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.35.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.36.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.36.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.36.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.36.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.37.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.37.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.37.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.37.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.38.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.38.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.38.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.38.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.39.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.39.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.39.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.39.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.4.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.4.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.4.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.4.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.40.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.40.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.40.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.40.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.41.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.41.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.41.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.41.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.42.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.42.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.42.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.42.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.43.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.43.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.43.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.43.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.44.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.44.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.44.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.44.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.45.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.45.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.45.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.45.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.46.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.46.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.46.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.46.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.47.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.47.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.47.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.47.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.48.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.48.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.48.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.48.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.49.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.49.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.49.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.49.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.5.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.5.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.5.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.5.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.50.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.50.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.50.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.50.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.51.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.51.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.51.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.51.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.52.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.52.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.52.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.52.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.53.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.53.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.53.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.53.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.54.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.54.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.54.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.54.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.55.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.55.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.55.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.55.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.56.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.56.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.56.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.56.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.57.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.57.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.57.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.57.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.58.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.58.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.58.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.58.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.59.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.59.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.59.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.59.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.6.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.6.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.6.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.6.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.60.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.60.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.60.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.60.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.61.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.61.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.61.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.61.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.62.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.62.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.62.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.62.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.63.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.63.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.63.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.63.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.64.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.64.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.64.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.64.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.65.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.65.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.65.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.65.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.66.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.66.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.66.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.66.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.67.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.67.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.67.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.67.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.68.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.68.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.68.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.68.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.69.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.69.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.69.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.69.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.7.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.7.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.7.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.7.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.70.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.70.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.70.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.70.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.71.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.71.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.71.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.71.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.72.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.72.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.72.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.72.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.73.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.73.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.73.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.73.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.74.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.74.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.74.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.74.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.75.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.75.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.75.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.75.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.76.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.76.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.76.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.76.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.77.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.77.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.77.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.77.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.78.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.78.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.78.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.78.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.79.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.79.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.79.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.79.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.8.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.8.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.8.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.8.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.80.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.80.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.80.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.80.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.81.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.81.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.81.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.81.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.82.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.82.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.82.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.82.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.83.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.83.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.83.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.83.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.84.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.84.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.84.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.84.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.85.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.85.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.85.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.85.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.86.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.86.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.86.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.86.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.87.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.87.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.87.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.87.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.88.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.88.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.88.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.88.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.89.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.89.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.89.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.89.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.9.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.9.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.9.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.9.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.90.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.90.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.90.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.90.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.91.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.91.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.91.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.91.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.92.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.92.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.92.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.92.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.93.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.93.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.93.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.93.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.94.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.94.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.94.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.94.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.95.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.95.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.95.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.95.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.96.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.96.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.96.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.96.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.97.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.97.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.97.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.97.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.98.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.98.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.98.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.98.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.99.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.99.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.99.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.8.mlp.experts.99.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.0.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.1.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.10.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.100.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.101.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.102.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.103.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.104.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.105.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.106.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.107.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.108.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.109.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.11.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.110.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.111.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.112.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.113.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.114.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.115.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.116.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.117.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.118.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.119.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.12.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.120.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.121.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.122.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.123.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.124.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.125.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.126.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.127.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.13.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.14.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.15.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.16.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.17.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.18.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.19.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.2.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.20.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.21.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.22.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.23.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.24.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.25.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.26.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.27.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.28.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.29.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.3.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.30.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.31.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.32.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.33.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.34.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.35.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.36.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.37.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.38.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.39.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.4.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.40.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.41.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.42.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.43.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.44.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.45.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.46.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.47.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.48.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.49.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.5.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.50.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.51.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.52.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.53.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.54.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.55.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.56.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.57.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.58.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.59.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.6.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.60.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.61.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.62.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.63.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.64.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.65.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.66.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.67.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.68.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.69.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.7.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.70.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.71.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.72.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.73.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.74.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.75.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.76.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.77.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.78.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.79.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.8.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.80.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.81.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.82.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.83.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.84.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.85.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.86.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.87.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.88.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.89.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.9.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.90.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.91.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.92.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.93.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.94.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.95.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.96.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.97.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.98.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.experts.99.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.gate.e_score_correction_bias": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.gate.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.shared_experts.down_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.shared_experts.gate_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00011-of-00048.safetensors",
+ "model.layers.9.mlp.shared_experts.up_proj.weight_scale": "model-00011-of-00048.safetensors",
+ "model.layers.31.mlp.experts.0.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.0.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.0.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.0.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.1.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.1.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.1.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.1.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.10.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.10.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.10.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.10.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.100.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.100.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.100.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.100.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.101.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.101.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.101.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.101.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.102.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.102.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.102.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.102.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.103.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.103.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.103.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.103.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.104.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.104.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.104.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.104.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.105.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.105.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.105.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.105.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.106.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.106.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.106.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.106.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.107.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.107.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.107.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.107.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.108.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.108.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.108.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.108.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.109.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.109.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.109.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.109.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.11.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.11.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.11.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.11.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.110.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.110.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.110.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.110.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.111.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.111.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.111.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.111.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.112.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.112.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.112.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.112.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.113.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.113.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.113.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.113.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.114.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.114.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.114.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.114.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.115.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.115.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.115.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.115.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.116.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.116.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.116.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.116.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.117.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.117.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.117.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.117.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.118.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.118.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.118.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.118.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.119.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.119.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.119.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.119.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.12.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.12.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.12.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.12.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.120.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.120.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.120.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.120.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.121.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.121.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.121.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.121.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.122.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.122.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.122.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.122.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.123.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.123.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.123.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.123.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.124.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.124.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.124.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.124.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.125.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.125.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.125.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.125.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.126.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.126.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.126.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.126.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.127.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.127.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.127.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.127.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.13.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.13.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.13.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.13.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.14.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.14.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.14.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.14.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.15.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.15.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.15.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.15.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.16.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.16.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.16.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.16.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.17.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.17.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.17.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.17.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.18.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.18.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.18.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.18.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.19.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.19.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.19.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.19.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.2.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.2.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.2.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.2.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.20.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.20.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.20.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.20.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.21.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.21.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.21.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.21.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.22.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.22.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.22.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.22.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.23.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.23.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.23.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.23.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.24.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.24.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.24.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.24.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.25.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.25.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.25.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.25.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.26.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.26.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.26.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.26.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.27.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.27.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.27.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.27.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.28.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.28.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.28.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.28.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.29.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.29.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.29.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.29.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.3.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.3.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.3.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.3.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.30.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.30.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.30.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.30.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.31.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.31.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.31.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.31.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.32.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.32.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.32.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.32.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.33.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.33.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.33.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.33.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.34.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.34.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.34.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.34.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.35.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.35.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.35.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.35.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.36.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.36.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.36.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.36.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.37.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.37.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.37.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.37.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.38.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.38.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.38.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.38.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.39.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.39.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.39.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.39.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.4.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.4.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.4.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.4.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.40.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.40.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.40.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.40.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.41.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.41.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.41.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.41.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.42.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.42.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.42.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.42.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.43.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.43.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.43.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.43.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.44.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.44.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.44.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.44.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.45.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.45.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.45.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.45.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.46.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.46.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.46.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.46.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.47.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.47.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.47.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.47.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.48.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.48.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.48.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.48.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.49.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.49.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.49.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.49.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.5.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.5.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.5.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.5.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.50.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.50.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.50.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.50.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.51.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.51.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.51.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.51.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.52.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.52.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.52.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.52.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.53.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.53.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.53.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.53.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.54.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.54.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.54.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.54.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.55.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.55.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.55.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.55.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.56.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.56.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.56.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.56.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.57.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.57.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.57.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.57.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.58.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.58.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.58.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.58.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.59.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.59.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.59.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.59.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.6.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.6.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.6.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.6.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.60.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.60.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.60.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.60.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.61.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.61.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.61.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.61.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.62.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.62.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.62.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.62.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.63.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.63.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.63.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.63.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.64.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.64.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.64.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.64.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.65.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.65.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.65.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.65.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.66.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.66.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.66.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.66.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.67.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.67.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.67.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.67.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.68.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.68.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.68.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.68.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.69.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.69.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.69.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.69.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.7.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.7.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.7.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.7.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.70.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.70.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.70.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.70.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.71.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.71.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.71.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.71.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.72.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.72.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.72.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.72.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.73.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.73.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.73.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.73.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.74.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.74.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.74.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.74.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.75.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.75.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.75.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.75.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.76.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.76.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.76.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.76.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.77.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.77.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.77.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.77.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.78.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.78.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.78.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.78.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.79.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.79.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.79.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.79.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.8.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.8.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.8.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.8.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.80.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.80.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.80.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.80.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.81.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.81.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.81.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.81.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.82.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.82.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.82.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.82.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.83.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.83.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.83.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.83.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.84.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.84.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.84.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.84.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.85.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.85.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.85.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.85.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.86.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.86.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.86.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.86.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.87.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.87.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.87.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.87.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.88.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.88.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.88.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.88.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.89.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.89.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.89.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.89.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.9.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.9.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.9.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.9.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.90.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.90.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.90.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.90.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.91.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.91.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.91.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.91.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.92.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.92.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.92.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.92.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.93.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.93.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.93.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.93.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.94.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.94.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.94.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.94.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.95.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.95.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.95.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.95.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.96.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.96.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.96.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.96.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.97.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.97.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.97.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.97.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.98.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.98.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.98.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.98.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.99.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.99.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.99.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.31.mlp.experts.99.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.0.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.1.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.10.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.100.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.100.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.101.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.101.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.102.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.102.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.103.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.103.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.104.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.104.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.105.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.105.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.106.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.106.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.107.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.107.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.108.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.108.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.109.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.109.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.11.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.110.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.110.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.111.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.111.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.112.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.112.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.113.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.113.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.114.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.114.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.115.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.115.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.116.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.116.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.117.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.117.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.118.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.118.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.119.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.119.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.12.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.120.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.120.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.121.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.121.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.122.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.122.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.123.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.123.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.124.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.124.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.125.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.125.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.126.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.126.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.127.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.127.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.13.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.14.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.15.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.16.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.17.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.18.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.19.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.2.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.20.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.21.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.22.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.23.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.24.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.25.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.26.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.27.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.28.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.29.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.3.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.30.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.31.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.32.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.33.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.34.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.35.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.36.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.37.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.38.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.39.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.4.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.40.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.41.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.42.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.43.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.44.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.45.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.46.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.47.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.48.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.49.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.5.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.50.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.51.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.52.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.53.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.54.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.55.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.56.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.57.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.58.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.59.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.6.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.60.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.61.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.62.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.63.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.64.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.64.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.65.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.65.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.66.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.66.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.67.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.67.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.68.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.68.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.69.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.69.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.7.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.70.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.70.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.71.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.71.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.72.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.72.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.73.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.73.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.74.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.74.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.75.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.75.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.76.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.76.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.77.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.77.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.78.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.78.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.79.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.79.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.8.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.80.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.80.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.81.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.81.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.82.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.82.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.83.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.83.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.84.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.84.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.85.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.85.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.86.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.86.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.87.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.87.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.88.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.88.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.89.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.89.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.9.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.90.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.90.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.91.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.91.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.92.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.92.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.93.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.93.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.94.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.94.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.95.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.95.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.96.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.96.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.97.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.97.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.98.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.98.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.99.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.experts.99.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.gate.e_score_correction_bias": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.gate.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.shared_experts.down_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.shared_experts.gate_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00034-of-00048.safetensors",
+ "model.layers.32.mlp.shared_experts.up_proj.weight_scale": "model-00034-of-00048.safetensors",
+ "model.layers.12.mlp.experts.0.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.0.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.0.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.0.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.1.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.1.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.1.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.1.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.10.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.10.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.10.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.10.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.100.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.100.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.100.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.100.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.101.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.101.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.101.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.101.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.102.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.102.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.102.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.102.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.103.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.103.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.103.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.103.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.104.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.104.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.104.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.104.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.105.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.105.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.105.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.105.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.106.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.106.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.106.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.106.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.107.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.107.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.107.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.107.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.108.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.108.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.108.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.108.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.109.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.109.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.109.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.109.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.11.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.11.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.11.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.11.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.110.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.110.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.110.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.110.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.111.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.111.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.111.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.111.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.112.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.112.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.112.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.112.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.113.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.113.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.113.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.113.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.114.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.114.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.114.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.114.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.115.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.115.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.115.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.115.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.116.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.116.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.116.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.116.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.117.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.117.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.117.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.117.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.118.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.118.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.118.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.118.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.119.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.119.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.119.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.119.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.12.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.12.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.12.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.12.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.120.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.120.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.120.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.120.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.121.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.121.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.121.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.121.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.122.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.122.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.122.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.122.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.123.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.123.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.123.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.123.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.124.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.124.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.124.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.124.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.125.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.125.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.125.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.125.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.126.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.126.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.126.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.126.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.127.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.127.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.127.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.127.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.13.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.13.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.13.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.13.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.14.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.14.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.14.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.14.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.15.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.15.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.15.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.15.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.16.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.16.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.16.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.16.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.17.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.17.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.17.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.17.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.18.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.18.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.18.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.18.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.19.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.19.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.19.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.19.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.2.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.2.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.2.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.2.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.20.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.20.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.20.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.20.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.21.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.21.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.21.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.21.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.22.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.22.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.22.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.22.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.23.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.23.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.23.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.23.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.24.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.24.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.24.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.24.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.25.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.25.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.25.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.25.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.26.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.26.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.26.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.26.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.27.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.27.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.27.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.27.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.28.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.28.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.28.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.28.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.29.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.29.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.29.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.29.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.3.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.3.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.3.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.3.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.30.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.30.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.30.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.30.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.31.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.31.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.31.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.31.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.32.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.32.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.32.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.32.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.33.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.33.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.33.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.33.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.34.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.34.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.34.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.34.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.35.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.35.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.35.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.35.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.36.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.36.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.36.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.36.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.37.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.37.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.37.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.37.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.38.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.38.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.38.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.38.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.39.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.39.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.39.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.39.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.4.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.4.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.4.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.4.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.40.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.40.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.40.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.40.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.41.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.41.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.41.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.41.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.42.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.42.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.42.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.42.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.43.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.43.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.43.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.43.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.44.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.44.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.44.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.44.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.45.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.45.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.45.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.45.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.46.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.46.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.46.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.46.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.47.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.47.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.47.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.47.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.48.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.48.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.48.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.48.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.49.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.49.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.49.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.49.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.5.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.5.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.5.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.5.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.50.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.50.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.50.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.50.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.51.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.51.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.51.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.51.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.52.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.52.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.52.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.52.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.53.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.53.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.53.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.53.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.54.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.54.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.54.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.54.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.55.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.55.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.55.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.55.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.56.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.56.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.56.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.56.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.57.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.57.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.57.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.57.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.58.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.58.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.58.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.58.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.59.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.59.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.59.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.59.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.6.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.6.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.6.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.6.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.60.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.60.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.60.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.60.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.61.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.61.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.61.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.61.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.62.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.62.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.62.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.62.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.63.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.63.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.63.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.63.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.64.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.64.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.64.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.64.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.65.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.65.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.65.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.65.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.66.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.66.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.66.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.66.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.67.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.67.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.67.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.67.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.68.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.68.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.68.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.68.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.69.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.69.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.69.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.69.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.7.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.7.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.7.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.7.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.70.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.70.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.70.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.70.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.71.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.71.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.71.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.71.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.72.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.72.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.72.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.72.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.73.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.73.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.73.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.73.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.74.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.74.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.74.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.74.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.75.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.75.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.75.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.75.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.76.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.76.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.76.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.76.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.77.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.77.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.77.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.77.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.78.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.78.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.78.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.78.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.79.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.79.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.79.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.79.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.8.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.8.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.8.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.8.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.80.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.80.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.80.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.80.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.81.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.81.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.81.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.81.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.82.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.82.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.82.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.82.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.83.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.83.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.83.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.83.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.84.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.84.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.84.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.84.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.85.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.85.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.85.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.85.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.86.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.86.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.86.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.86.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.87.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.87.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.87.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.87.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.88.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.88.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.88.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.88.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.89.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.89.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.89.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.89.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.9.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.9.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.9.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.9.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.90.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.90.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.90.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.90.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.91.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.91.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.91.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.91.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.92.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.92.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.92.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.92.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.93.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.93.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.93.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.93.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.94.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.94.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.94.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.94.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.95.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.95.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.95.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.95.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.96.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.96.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.96.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.96.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.97.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.97.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.97.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.97.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.98.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.98.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.98.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.98.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.99.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.99.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.99.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.12.mlp.experts.99.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.0.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.1.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.10.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.100.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.101.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.102.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.103.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.104.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.105.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.106.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.107.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.108.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.109.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.11.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.110.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.111.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.112.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.113.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.114.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.115.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.116.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.117.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.118.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.119.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.12.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.120.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.121.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.122.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.123.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.124.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.125.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.126.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.127.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.13.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.14.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.15.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.16.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.17.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.18.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.19.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.2.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.20.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.21.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.22.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.23.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.24.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.25.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.26.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.27.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.28.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.29.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.3.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.30.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.31.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.32.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.33.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.34.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.35.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.36.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.37.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.38.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.39.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.4.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.40.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.41.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.42.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.43.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.44.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.45.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.46.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.47.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.48.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.49.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.5.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.50.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.51.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.52.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.53.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.54.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.55.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.56.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.57.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.58.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.59.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.6.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.60.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.61.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.62.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.63.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.64.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.65.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.66.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.67.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.68.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.69.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.7.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.70.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.71.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.72.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.73.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.74.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.75.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.76.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.77.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.78.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.79.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.8.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.80.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.81.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.82.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.83.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.84.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.85.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.86.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.87.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.88.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.89.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.9.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.90.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.91.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.92.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.93.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.94.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.95.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.96.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.97.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.98.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.experts.99.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.gate.e_score_correction_bias": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.gate.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.shared_experts.down_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.shared_experts.gate_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00015-of-00048.safetensors",
+ "model.layers.13.mlp.shared_experts.up_proj.weight_scale": "model-00015-of-00048.safetensors",
+ "model.layers.20.mlp.experts.0.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.0.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.0.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.0.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.1.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.1.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.1.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.1.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.10.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.10.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.10.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.10.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.100.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.100.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.100.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.100.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.101.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.101.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.101.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.101.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.102.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.102.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.102.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.102.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.103.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.103.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.103.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.103.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.104.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.104.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.104.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.104.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.105.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.105.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.105.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.105.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.106.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.106.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.106.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.106.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.107.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.107.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.107.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.107.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.108.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.108.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.108.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.108.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.109.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.109.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.109.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.109.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.11.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.11.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.11.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.11.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.110.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.110.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.110.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.110.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.111.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.111.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.111.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.111.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.112.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.112.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.112.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.112.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.113.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.113.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.113.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.113.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.114.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.114.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.114.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.114.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.115.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.115.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.115.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.115.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.116.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.116.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.116.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.116.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.117.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.117.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.117.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.117.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.118.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.118.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.118.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.118.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.119.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.119.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.119.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.119.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.12.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.12.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.12.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.12.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.120.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.120.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.120.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.120.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.121.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.121.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.121.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.121.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.122.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.122.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.122.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.122.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.123.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.123.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.123.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.123.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.124.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.124.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.124.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.124.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.125.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.125.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.125.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.125.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.126.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.126.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.126.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.126.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.127.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.127.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.127.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.127.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.13.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.13.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.13.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.13.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.14.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.14.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.14.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.14.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.15.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.15.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.15.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.15.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.16.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.16.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.16.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.16.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.17.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.17.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.17.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.17.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.18.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.18.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.18.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.18.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.19.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.19.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.19.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.19.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.2.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.2.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.2.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.2.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.20.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.20.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.20.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.20.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.21.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.21.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.21.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.21.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.22.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.22.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.22.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.22.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.23.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.23.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.23.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.23.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.24.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.24.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.24.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.24.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.25.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.25.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.25.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.25.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.26.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.26.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.26.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.26.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.27.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.27.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.27.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.27.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.28.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.28.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.28.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.28.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.29.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.29.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.29.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.29.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.3.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.3.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.3.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.3.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.30.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.30.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.30.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.30.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.31.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.31.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.31.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.31.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.32.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.32.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.32.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.32.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.33.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.33.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.33.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.33.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.34.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.34.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.34.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.34.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.35.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.35.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.35.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.35.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.36.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.36.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.36.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.36.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.37.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.37.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.37.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.37.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.38.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.38.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.38.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.38.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.39.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.39.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.39.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.39.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.4.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.4.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.4.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.4.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.40.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.40.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.40.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.40.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.41.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.41.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.41.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.41.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.42.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.42.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.42.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.42.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.43.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.43.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.43.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.43.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.44.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.44.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.44.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.44.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.45.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.45.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.45.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.45.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.46.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.46.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.46.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.46.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.47.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.47.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.47.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.47.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.48.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.48.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.48.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.48.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.49.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.49.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.49.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.49.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.5.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.5.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.5.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.5.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.50.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.50.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.50.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.50.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.51.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.51.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.51.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.51.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.52.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.52.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.52.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.52.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.53.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.53.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.53.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.53.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.54.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.54.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.54.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.54.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.55.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.55.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.55.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.55.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.56.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.56.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.56.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.56.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.57.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.57.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.57.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.57.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.58.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.58.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.58.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.58.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.59.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.59.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.59.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.59.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.6.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.6.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.6.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.6.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.60.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.60.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.60.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.60.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.61.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.61.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.61.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.61.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.62.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.62.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.62.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.62.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.63.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.63.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.63.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.63.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.64.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.64.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.64.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.64.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.65.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.65.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.65.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.65.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.66.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.66.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.66.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.66.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.67.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.67.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.67.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.67.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.68.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.68.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.68.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.68.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.69.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.69.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.69.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.69.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.7.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.7.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.7.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.7.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.70.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.70.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.70.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.70.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.71.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.71.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.71.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.71.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.72.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.72.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.72.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.72.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.73.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.73.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.73.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.73.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.74.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.74.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.74.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.74.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.75.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.75.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.75.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.75.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.76.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.76.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.76.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.76.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.77.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.77.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.77.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.77.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.78.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.78.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.78.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.78.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.79.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.79.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.79.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.79.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.8.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.8.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.8.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.8.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.80.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.80.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.80.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.80.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.81.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.81.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.81.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.81.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.82.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.82.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.82.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.82.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.83.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.83.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.83.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.83.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.84.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.84.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.84.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.84.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.85.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.85.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.85.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.85.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.86.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.86.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.86.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.86.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.87.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.87.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.87.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.87.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.88.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.88.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.88.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.88.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.89.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.89.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.89.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.89.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.9.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.9.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.9.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.9.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.90.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.90.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.90.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.90.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.91.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.91.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.91.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.91.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.92.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.92.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.92.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.92.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.93.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.93.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.93.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.93.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.94.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.94.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.94.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.94.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.95.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.95.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.95.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.95.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.96.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.96.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.96.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.96.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.97.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.97.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.97.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.97.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.98.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.98.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.98.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.98.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.99.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.99.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.99.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.20.mlp.experts.99.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.0.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.1.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.10.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.100.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.101.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.102.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.103.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.104.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.105.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.106.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.107.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.108.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.109.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.11.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.110.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.111.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.112.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.113.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.114.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.115.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.116.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.117.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.118.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.119.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.12.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.120.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.121.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.122.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.123.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.124.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.125.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.126.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.127.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.13.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.14.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.15.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.16.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.17.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.18.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.19.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.2.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.20.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.21.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.22.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.23.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.24.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.25.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.26.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.27.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.28.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.29.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.3.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.30.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.31.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.32.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.33.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.34.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.35.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.36.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.37.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.38.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.39.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.4.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.40.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.41.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.42.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.43.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.44.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.45.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.46.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.47.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.48.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.49.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.5.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.50.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.51.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.52.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.53.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.54.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.55.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.56.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.57.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.58.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.59.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.6.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.60.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.61.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.62.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.63.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.64.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.65.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.66.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.67.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.68.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.69.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.7.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.70.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.71.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.72.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.73.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.74.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.75.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.76.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.77.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.78.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.79.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.8.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.80.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.81.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.82.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.83.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.84.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.85.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.86.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.87.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.88.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.89.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.9.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.90.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.91.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.92.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.93.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.94.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.95.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.96.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.97.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.98.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.experts.99.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.gate.e_score_correction_bias": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.gate.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.shared_experts.down_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.shared_experts.gate_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00023-of-00048.safetensors",
+ "model.layers.21.mlp.shared_experts.up_proj.weight_scale": "model-00023-of-00048.safetensors",
+ "model.layers.1.mlp.experts.0.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.0.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.0.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.0.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.1.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.1.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.1.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.1.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.10.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.10.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.10.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.10.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.100.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.100.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.100.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.100.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.101.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.101.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.101.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.101.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.102.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.102.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.102.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.102.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.103.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.103.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.103.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.103.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.104.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.104.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.104.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.104.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.105.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.105.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.105.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.105.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.106.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.106.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.106.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.106.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.107.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.107.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.107.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.107.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.108.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.108.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.108.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.108.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.109.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.109.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.109.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.109.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.11.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.11.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.11.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.11.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.110.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.110.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.110.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.110.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.111.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.111.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.111.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.111.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.112.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.112.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.112.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.112.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.113.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.113.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.113.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.113.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.114.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.114.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.114.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.114.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.115.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.115.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.115.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.115.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.116.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.116.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.116.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.116.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.117.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.117.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.117.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.117.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.118.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.118.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.118.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.118.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.119.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.119.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.119.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.119.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.12.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.12.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.12.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.12.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.120.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.120.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.120.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.120.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.121.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.121.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.121.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.121.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.122.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.122.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.122.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.122.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.123.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.123.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.123.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.123.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.124.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.124.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.124.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.124.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.125.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.125.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.125.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.125.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.126.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.126.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.126.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.126.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.127.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.127.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.127.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.127.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.13.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.13.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.13.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.13.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.14.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.14.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.14.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.14.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.15.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.15.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.15.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.15.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.16.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.16.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.16.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.16.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.17.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.17.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.17.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.17.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.18.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.18.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.18.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.18.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.19.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.19.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.19.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.19.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.2.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.2.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.2.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.2.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.20.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.20.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.20.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.20.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.21.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.21.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.21.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.21.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.22.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.22.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.22.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.22.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.23.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.23.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.23.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.23.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.24.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.24.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.24.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.24.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.25.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.25.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.25.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.25.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.26.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.26.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.26.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.26.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.27.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.27.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.27.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.27.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.28.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.28.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.28.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.28.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.29.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.29.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.29.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.29.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.3.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.3.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.3.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.3.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.30.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.30.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.30.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.30.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.31.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.31.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.31.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.31.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.32.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.32.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.32.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.32.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.33.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.33.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.33.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.33.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.34.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.34.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.34.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.34.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.35.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.35.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.35.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.35.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.36.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.36.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.36.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.36.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.37.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.37.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.37.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.37.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.38.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.38.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.38.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.38.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.39.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.39.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.39.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.39.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.4.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.4.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.4.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.4.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.40.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.40.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.40.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.40.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.41.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.41.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.41.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.41.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.42.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.42.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.42.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.42.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.43.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.43.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.43.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.43.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.44.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.44.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.44.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.44.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.45.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.45.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.45.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.45.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.46.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.46.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.46.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.46.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.47.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.47.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.47.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.47.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.48.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.48.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.48.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.48.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.49.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.49.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.49.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.49.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.5.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.5.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.5.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.5.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.50.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.50.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.50.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.50.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.51.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.51.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.51.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.51.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.52.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.52.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.52.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.52.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.53.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.53.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.53.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.53.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.54.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.54.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.54.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.54.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.55.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.55.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.55.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.55.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.56.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.56.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.56.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.56.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.57.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.57.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.57.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.57.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.58.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.58.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.58.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.58.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.59.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.59.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.59.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.59.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.6.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.6.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.6.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.6.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.60.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.60.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.60.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.60.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.61.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.61.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.61.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.61.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.62.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.62.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.62.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.62.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.63.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.63.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.63.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.63.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.64.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.64.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.64.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.64.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.65.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.65.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.65.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.65.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.66.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.66.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.66.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.66.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.67.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.67.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.67.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.67.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.68.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.68.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.68.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.68.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.69.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.69.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.69.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.69.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.7.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.7.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.7.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.7.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.70.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.70.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.70.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.70.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.71.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.71.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.71.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.71.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.72.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.72.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.72.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.72.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.73.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.73.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.73.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.73.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.74.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.74.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.74.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.74.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.75.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.75.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.75.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.75.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.76.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.76.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.76.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.76.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.77.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.77.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.77.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.77.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.78.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.78.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.78.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.78.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.79.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.79.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.79.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.79.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.8.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.8.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.8.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.8.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.80.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.80.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.80.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.80.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.81.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.81.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.81.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.81.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.82.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.82.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.82.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.82.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.83.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.83.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.83.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.83.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.84.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.84.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.84.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.84.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.85.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.85.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.85.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.85.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.86.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.86.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.86.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.86.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.87.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.87.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.87.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.87.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.88.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.88.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.88.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.88.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.89.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.89.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.89.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.89.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.9.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.9.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.9.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.9.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.90.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.90.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.90.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.90.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.91.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.91.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.91.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.91.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.92.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.92.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.92.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.92.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.93.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.93.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.93.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.93.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.94.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.94.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.94.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.94.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.95.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.95.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.95.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.95.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.96.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.96.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.96.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.96.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.97.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.97.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.97.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.97.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.98.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.98.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.98.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.98.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.99.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.99.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.99.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.1.mlp.experts.99.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.0.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.1.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.10.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.100.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.100.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.101.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.101.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.102.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.102.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.103.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.103.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.104.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.104.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.105.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.105.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.106.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.106.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.107.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.107.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.108.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.108.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.109.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.109.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.11.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.110.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.110.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.111.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.111.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.112.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.112.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.113.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.113.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.114.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.114.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.115.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.115.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.116.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.116.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.117.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.117.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.118.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.118.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.119.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.119.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.12.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.120.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.120.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.121.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.121.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.122.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.122.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.123.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.123.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.124.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.124.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.125.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.125.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.126.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.126.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.127.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.127.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.13.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.14.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.15.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.16.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.17.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.18.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.19.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.2.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.20.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.21.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.22.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.23.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.24.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.25.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.26.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.27.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.28.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.29.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.3.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.30.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.31.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.32.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.33.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.34.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.35.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.36.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.37.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.38.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.39.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.4.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.40.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.41.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.42.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.43.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.44.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.45.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.46.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.47.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.48.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.49.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.5.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.50.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.51.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.52.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.53.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.54.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.55.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.56.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.57.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.58.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.59.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.6.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.60.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.61.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.62.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.63.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.64.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.64.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.65.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.65.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.66.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.66.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.67.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.67.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.68.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.68.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.69.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.69.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.7.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.70.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.70.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.71.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.71.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.72.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.72.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.73.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.73.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.74.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.74.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.75.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.75.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.76.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.76.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.77.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.77.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.78.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.78.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.79.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.79.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.8.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.80.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.80.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.81.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.81.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.82.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.82.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.83.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.83.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.84.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.84.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.85.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.85.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.86.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.86.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.87.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.87.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.88.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.88.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.89.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.89.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.9.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.90.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.90.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.91.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.91.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.92.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.92.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.93.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.93.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.94.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.94.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.95.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.95.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.96.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.96.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.97.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.97.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.98.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.98.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.99.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.experts.99.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.gate.e_score_correction_bias": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.gate.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.shared_experts.down_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.shared_experts.gate_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00004-of-00048.safetensors",
+ "model.layers.2.mlp.shared_experts.up_proj.weight_scale": "model-00004-of-00048.safetensors",
+ "model.layers.15.mlp.experts.0.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.0.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.0.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.0.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.1.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.1.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.1.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.1.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.10.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.10.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.10.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.10.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.100.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.100.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.100.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.100.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.101.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.101.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.101.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.101.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.102.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.102.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.102.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.102.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.103.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.103.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.103.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.103.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.104.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.104.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.104.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.104.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.105.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.105.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.105.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.105.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.106.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.106.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.106.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.106.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.107.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.107.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.107.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.107.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.108.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.108.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.108.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.108.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.109.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.109.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.109.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.109.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.11.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.11.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.11.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.11.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.110.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.110.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.110.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.110.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.111.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.111.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.111.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.111.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.112.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.112.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.112.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.112.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.113.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.113.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.113.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.113.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.114.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.114.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.114.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.114.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.115.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.115.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.115.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.115.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.116.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.116.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.116.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.116.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.117.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.117.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.117.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.117.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.118.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.118.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.118.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.118.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.119.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.119.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.119.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.119.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.12.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.12.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.12.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.12.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.120.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.120.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.120.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.120.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.121.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.121.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.121.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.121.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.122.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.122.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.122.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.122.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.123.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.123.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.123.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.123.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.124.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.124.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.124.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.124.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.125.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.125.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.125.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.125.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.126.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.126.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.126.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.126.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.127.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.127.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.127.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.127.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.13.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.13.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.13.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.13.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.14.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.14.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.14.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.14.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.15.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.15.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.15.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.15.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.16.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.16.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.16.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.16.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.17.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.17.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.17.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.17.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.18.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.18.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.18.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.18.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.19.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.19.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.19.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.19.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.2.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.2.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.2.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.2.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.20.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.20.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.20.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.20.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.21.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.21.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.21.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.21.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.22.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.22.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.22.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.22.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.23.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.23.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.23.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.23.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.24.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.24.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.24.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.24.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.25.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.25.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.25.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.25.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.26.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.26.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.26.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.26.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.27.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.27.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.27.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.27.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.28.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.28.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.28.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.28.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.29.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.29.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.29.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.29.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.3.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.3.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.3.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.3.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.30.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.30.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.30.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.30.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.31.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.31.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.31.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.31.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.32.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.32.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.32.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.32.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.33.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.33.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.33.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.33.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.34.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.34.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.34.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.34.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.35.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.35.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.35.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.35.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.36.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.36.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.36.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.36.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.37.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.37.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.37.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.37.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.38.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.38.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.38.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.38.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.39.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.39.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.39.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.39.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.4.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.4.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.4.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.4.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.40.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.40.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.40.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.40.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.41.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.41.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.41.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.41.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.42.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.42.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.42.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.42.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.43.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.43.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.43.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.43.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.44.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.44.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.44.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.44.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.45.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.45.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.45.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.45.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.46.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.46.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.46.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.46.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.47.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.47.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.47.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.47.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.48.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.48.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.48.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.48.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.49.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.49.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.49.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.49.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.5.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.5.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.5.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.5.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.50.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.50.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.50.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.50.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.51.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.51.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.51.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.51.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.52.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.52.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.52.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.52.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.53.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.53.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.53.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.53.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.54.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.54.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.54.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.54.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.55.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.55.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.55.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.55.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.56.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.56.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.56.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.56.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.57.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.57.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.57.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.57.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.58.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.58.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.58.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.58.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.59.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.59.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.59.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.59.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.6.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.6.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.6.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.6.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.60.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.60.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.60.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.60.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.61.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.61.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.61.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.61.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.62.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.62.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.62.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.62.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.63.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.63.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.63.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.63.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.64.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.64.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.64.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.64.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.65.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.65.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.65.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.65.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.66.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.66.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.66.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.66.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.67.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.67.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.67.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.67.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.68.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.68.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.68.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.68.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.69.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.69.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.69.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.69.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.7.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.7.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.7.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.7.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.70.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.70.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.70.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.70.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.71.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.71.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.71.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.71.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.72.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.72.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.72.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.72.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.73.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.73.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.73.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.73.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.74.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.74.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.74.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.74.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.75.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.75.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.75.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.75.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.76.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.76.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.76.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.76.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.77.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.77.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.77.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.77.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.78.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.78.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.78.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.78.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.79.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.79.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.79.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.79.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.8.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.8.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.8.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.8.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.80.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.80.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.80.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.80.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.81.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.81.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.81.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.81.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.82.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.82.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.82.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.82.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.83.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.83.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.83.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.83.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.84.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.84.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.84.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.84.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.85.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.85.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.85.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.85.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.86.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.86.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.86.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.86.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.87.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.87.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.87.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.87.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.88.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.88.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.88.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.88.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.89.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.89.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.89.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.89.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.9.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.9.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.9.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.9.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.90.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.90.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.90.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.90.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.91.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.91.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.91.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.91.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.92.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.92.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.92.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.92.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.93.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.93.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.93.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.93.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.94.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.94.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.94.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.94.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.95.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.95.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.95.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.95.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.96.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.96.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.96.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.96.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.97.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.97.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.97.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.97.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.98.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.98.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.98.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.98.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.99.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.99.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.99.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.15.mlp.experts.99.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.0.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.1.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.10.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.100.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.101.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.102.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.103.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.104.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.105.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.106.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.107.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.108.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.109.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.11.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.110.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.111.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.112.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.113.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.114.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.115.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.116.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.117.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.118.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.119.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.12.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.120.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.121.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.122.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.123.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.124.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.125.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.126.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.127.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.13.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.14.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.15.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.16.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.17.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.18.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.19.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.2.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.20.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.21.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.22.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.23.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.24.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.25.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.26.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.27.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.28.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.29.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.3.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.30.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.31.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.32.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.33.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.34.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.35.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.36.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.37.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.38.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.39.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.4.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.40.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.41.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.42.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.43.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.44.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.45.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.46.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.47.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.48.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.49.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.5.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.50.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.51.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.52.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.53.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.54.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.55.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.56.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.57.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.58.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.59.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.6.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.60.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.61.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.62.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.63.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.64.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.65.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.66.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.67.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.68.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.69.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.7.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.70.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.71.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.72.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.73.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.74.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.75.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.76.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.77.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.78.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.79.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.8.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.80.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.81.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.82.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.83.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.84.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.85.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.86.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.87.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.88.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.89.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.9.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.90.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.91.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.92.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.93.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.94.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.95.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.96.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.97.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.98.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.experts.99.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.gate.e_score_correction_bias": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.gate.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.shared_experts.down_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.shared_experts.gate_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00018-of-00048.safetensors",
+ "model.layers.16.mlp.shared_experts.up_proj.weight_scale": "model-00018-of-00048.safetensors",
+ "model.layers.11.mlp.experts.0.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.0.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.0.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.0.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.1.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.1.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.1.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.1.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.10.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.10.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.10.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.10.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.100.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.100.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.100.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.100.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.101.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.101.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.101.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.101.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.102.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.102.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.102.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.102.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.103.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.103.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.103.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.103.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.104.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.104.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.104.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.104.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.105.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.105.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.105.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.105.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.106.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.106.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.106.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.106.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.107.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.107.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.107.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.107.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.108.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.108.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.108.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.108.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.109.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.109.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.109.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.109.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.11.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.11.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.11.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.11.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.110.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.110.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.110.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.110.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.111.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.111.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.111.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.111.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.112.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.112.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.112.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.112.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.113.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.113.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.113.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.113.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.114.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.114.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.114.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.114.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.115.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.115.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.115.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.115.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.116.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.116.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.116.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.116.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.117.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.117.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.117.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.117.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.118.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.118.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.118.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.118.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.119.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.119.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.119.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.119.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.12.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.12.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.12.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.12.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.120.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.120.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.120.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.120.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.121.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.121.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.121.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.121.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.122.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.122.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.122.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.122.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.123.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.123.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.123.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.123.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.124.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.124.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.124.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.124.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.125.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.125.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.125.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.125.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.126.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.126.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.126.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.126.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.127.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.127.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.127.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.127.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.13.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.13.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.13.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.13.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.14.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.14.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.14.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.14.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.15.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.15.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.15.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.15.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.16.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.16.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.16.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.16.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.17.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.17.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.17.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.17.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.18.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.18.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.18.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.18.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.19.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.19.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.19.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.19.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.2.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.2.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.2.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.2.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.20.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.20.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.20.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.20.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.21.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.21.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.21.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.21.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.22.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.22.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.22.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.22.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.23.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.23.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.23.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.23.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.24.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.24.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.24.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.24.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.25.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.25.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.25.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.25.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.26.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.26.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.26.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.26.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.27.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.27.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.27.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.27.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.28.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.28.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.28.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.28.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.29.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.29.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.29.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.29.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.3.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.3.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.3.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.3.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.30.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.30.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.30.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.30.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.31.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.31.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.31.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.31.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.32.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.32.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.32.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.32.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.33.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.33.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.33.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.33.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.34.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.34.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.34.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.34.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.35.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.35.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.35.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.35.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.36.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.36.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.36.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.36.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.37.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.37.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.37.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.37.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.38.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.38.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.38.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.38.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.39.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.39.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.39.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.39.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.4.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.4.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.4.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.4.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.40.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.40.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.40.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.40.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.41.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.41.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.41.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.41.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.42.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.42.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.42.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.42.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.43.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.43.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.43.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.43.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.44.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.44.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.44.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.44.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.45.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.45.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.45.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.45.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.46.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.46.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.46.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.46.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.47.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.47.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.47.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.47.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.48.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.48.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.48.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.48.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.49.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.49.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.49.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.49.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.5.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.5.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.5.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.5.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.50.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.50.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.50.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.50.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.51.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.51.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.51.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.51.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.52.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.52.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.52.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.52.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.53.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.53.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.53.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.53.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.54.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.54.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.54.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.54.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.55.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.55.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.55.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.55.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.56.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.56.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.56.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.56.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.57.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.57.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.57.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.57.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.58.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.58.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.58.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.58.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.59.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.59.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.59.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.59.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.6.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.6.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.6.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.6.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.60.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.60.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.60.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.60.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.61.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.61.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.61.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.61.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.62.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.62.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.62.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.62.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.63.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.63.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.63.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.63.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.64.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.64.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.64.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.64.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.65.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.65.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.65.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.65.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.66.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.66.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.66.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.66.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.67.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.67.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.67.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.67.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.68.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.68.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.68.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.68.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.69.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.69.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.69.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.69.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.7.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.7.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.7.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.7.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.70.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.70.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.70.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.70.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.71.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.71.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.71.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.71.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.72.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.72.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.72.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.72.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.73.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.73.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.73.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.73.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.74.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.74.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.74.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.74.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.75.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.75.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.75.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.75.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.76.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.76.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.76.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.76.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.77.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.77.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.77.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.77.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.78.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.78.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.78.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.78.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.79.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.79.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.79.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.79.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.8.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.8.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.8.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.8.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.80.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.80.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.80.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.80.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.81.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.81.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.81.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.81.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.82.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.82.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.82.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.82.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.83.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.83.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.83.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.83.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.84.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.84.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.84.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.84.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.85.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.85.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.85.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.85.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.86.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.86.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.86.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.86.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.87.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.87.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.87.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.87.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.88.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.88.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.88.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.88.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.89.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.89.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.89.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.89.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.9.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.9.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.9.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.9.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.90.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.90.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.90.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.90.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.91.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.91.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.91.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.91.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.92.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.92.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.92.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.92.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.93.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.93.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.93.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.93.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.94.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.94.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.94.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.94.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.95.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.95.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.95.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.95.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.96.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.96.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.96.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.96.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.97.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.97.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.97.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.97.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.98.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.98.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.98.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.98.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.99.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.99.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.99.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.11.mlp.experts.99.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.0.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.1.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.10.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.100.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.101.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.102.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.103.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.104.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.105.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.106.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.107.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.108.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.109.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.11.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.110.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.111.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.112.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.113.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.114.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.115.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.116.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.117.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.118.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.119.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.12.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.120.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.121.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.122.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.123.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.124.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.125.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.126.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.127.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.13.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.14.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.15.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.16.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.17.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.18.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.19.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.2.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.20.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.21.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.22.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.23.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.24.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.25.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.26.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.27.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.28.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.29.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.3.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.30.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.31.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.32.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.33.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.34.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.35.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.36.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.37.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.38.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.39.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.4.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.40.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.41.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.42.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.43.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.44.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.45.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.46.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.47.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.48.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.49.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.5.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.50.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.51.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.52.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.53.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.54.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.55.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.56.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.57.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.58.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.59.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.6.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.60.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.61.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.62.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.63.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.64.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.65.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.66.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.67.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.68.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.69.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.7.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.70.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.71.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.72.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.73.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.74.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.75.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.76.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.77.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.78.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.79.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.8.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.80.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.81.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.82.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.83.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.84.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.85.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.86.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.87.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.88.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.89.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.9.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.90.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.91.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.92.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.93.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.94.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.95.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.96.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.97.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.98.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.experts.99.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.gate.e_score_correction_bias": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.gate.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.shared_experts.down_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.shared_experts.gate_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00014-of-00048.safetensors",
+ "model.layers.12.mlp.shared_experts.up_proj.weight_scale": "model-00014-of-00048.safetensors",
+ "model.layers.28.mlp.experts.0.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.0.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.0.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.0.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.1.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.1.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.1.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.1.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.10.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.10.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.10.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.10.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.100.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.100.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.100.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.100.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.101.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.101.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.101.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.101.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.102.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.102.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.102.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.102.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.103.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.103.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.103.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.103.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.104.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.104.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.104.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.104.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.105.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.105.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.105.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.105.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.106.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.106.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.106.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.106.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.107.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.107.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.107.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.107.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.108.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.108.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.108.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.108.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.109.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.109.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.109.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.109.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.11.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.11.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.11.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.11.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.110.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.110.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.110.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.110.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.111.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.111.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.111.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.111.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.112.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.112.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.112.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.112.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.113.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.113.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.113.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.113.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.114.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.114.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.114.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.114.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.115.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.115.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.115.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.115.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.116.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.116.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.116.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.116.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.117.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.117.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.117.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.117.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.118.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.118.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.118.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.118.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.119.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.119.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.119.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.119.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.12.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.12.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.12.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.12.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.120.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.120.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.120.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.120.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.121.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.121.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.121.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.121.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.122.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.122.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.122.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.122.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.123.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.123.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.123.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.123.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.124.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.124.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.124.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.124.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.125.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.125.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.125.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.125.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.126.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.126.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.126.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.126.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.127.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.127.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.127.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.127.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.13.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.13.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.13.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.13.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.14.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.14.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.14.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.14.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.15.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.15.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.15.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.15.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.16.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.16.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.16.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.16.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.17.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.17.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.17.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.17.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.18.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.18.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.18.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.18.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.19.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.19.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.19.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.19.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.2.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.2.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.2.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.2.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.20.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.20.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.20.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.20.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.21.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.21.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.21.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.21.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.22.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.22.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.22.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.22.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.23.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.23.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.23.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.23.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.24.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.24.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.24.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.24.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.25.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.25.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.25.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.25.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.26.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.26.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.26.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.26.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.27.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.27.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.27.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.27.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.28.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.28.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.28.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.28.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.29.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.29.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.29.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.29.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.3.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.3.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.3.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.3.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.30.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.30.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.30.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.30.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.31.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.31.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.31.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.31.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.32.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.32.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.32.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.32.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.33.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.33.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.33.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.33.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.34.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.34.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.34.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.34.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.35.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.35.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.35.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.35.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.36.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.36.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.36.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.36.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.37.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.37.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.37.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.37.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.38.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.38.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.38.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.38.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.39.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.39.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.39.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.39.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.4.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.4.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.4.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.4.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.40.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.40.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.40.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.40.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.41.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.41.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.41.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.41.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.42.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.42.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.42.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.42.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.43.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.43.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.43.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.43.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.44.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.44.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.44.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.44.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.45.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.45.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.45.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.45.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.46.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.46.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.46.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.46.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.47.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.47.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.47.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.47.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.48.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.48.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.48.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.48.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.49.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.49.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.49.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.49.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.5.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.5.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.5.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.5.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.50.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.50.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.50.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.50.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.51.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.51.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.51.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.51.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.52.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.52.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.52.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.52.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.53.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.53.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.53.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.53.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.54.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.54.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.54.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.54.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.55.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.55.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.55.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.55.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.56.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.56.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.56.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.56.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.57.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.57.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.57.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.57.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.58.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.58.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.58.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.58.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.59.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.59.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.59.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.59.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.6.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.6.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.6.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.6.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.60.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.60.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.60.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.60.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.61.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.61.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.61.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.61.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.62.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.62.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.62.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.62.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.63.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.63.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.63.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.63.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.64.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.64.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.64.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.64.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.65.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.65.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.65.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.65.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.66.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.66.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.66.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.66.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.67.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.67.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.67.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.67.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.68.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.68.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.68.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.68.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.69.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.69.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.69.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.69.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.7.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.7.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.7.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.7.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.70.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.70.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.70.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.70.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.71.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.71.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.71.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.71.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.72.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.72.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.72.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.72.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.73.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.73.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.73.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.73.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.74.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.74.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.74.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.74.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.75.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.75.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.75.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.75.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.76.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.76.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.76.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.76.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.77.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.77.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.77.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.77.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.78.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.78.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.78.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.78.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.79.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.79.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.79.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.79.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.8.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.8.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.8.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.8.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.80.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.80.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.80.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.80.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.81.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.81.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.81.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.81.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.82.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.82.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.82.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.82.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.83.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.83.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.83.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.83.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.84.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.84.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.84.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.84.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.85.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.85.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.85.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.85.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.86.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.86.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.86.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.86.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.87.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.87.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.87.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.87.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.88.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.88.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.88.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.88.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.89.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.89.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.89.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.89.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.9.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.9.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.9.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.9.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.90.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.90.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.90.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.90.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.91.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.91.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.91.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.91.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.92.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.92.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.92.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.92.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.93.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.93.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.93.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.93.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.94.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.94.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.94.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.94.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.95.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.95.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.95.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.95.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.96.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.96.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.96.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.96.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.97.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.97.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.97.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.97.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.98.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.98.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.98.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.98.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.99.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.99.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.99.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.28.mlp.experts.99.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.0.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.1.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.10.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.100.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.101.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.102.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.103.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.104.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.105.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.106.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.107.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.108.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.109.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.11.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.110.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.111.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.112.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.113.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.114.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.115.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.116.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.117.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.118.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.119.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.12.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.120.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.121.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.122.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.123.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.124.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.125.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.126.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.127.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.13.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.14.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.15.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.16.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.17.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.18.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.19.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.2.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.20.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.21.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.22.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.23.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.24.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.25.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.26.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.27.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.28.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.29.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.3.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.30.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.31.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.32.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.33.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.34.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.35.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.36.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.37.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.38.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.39.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.4.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.40.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.41.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.42.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.43.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.44.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.45.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.46.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.47.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.48.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.49.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.5.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.50.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.51.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.52.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.53.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.54.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.55.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.56.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.57.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.58.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.59.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.6.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.60.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.61.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.62.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.63.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.64.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.65.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.66.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.67.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.68.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.69.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.7.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.70.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.71.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.72.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.73.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.74.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.75.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.76.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.77.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.78.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.79.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.8.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.80.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.81.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.82.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.83.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.84.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.85.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.86.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.87.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.88.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.89.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.9.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.90.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.91.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.92.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.93.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.94.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.95.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.96.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.97.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.98.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.experts.99.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.gate.e_score_correction_bias": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.gate.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.shared_experts.down_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.shared_experts.gate_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00031-of-00048.safetensors",
+ "model.layers.29.mlp.shared_experts.up_proj.weight_scale": "model-00031-of-00048.safetensors",
+ "model.layers.25.mlp.experts.0.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.0.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.0.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.0.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.1.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.1.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.1.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.1.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.10.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.10.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.10.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.10.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.100.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.100.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.100.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.100.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.101.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.101.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.101.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.101.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.102.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.102.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.102.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.102.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.103.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.103.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.103.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.103.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.104.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.104.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.104.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.104.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.105.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.105.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.105.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.105.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.106.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.106.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.106.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.106.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.107.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.107.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.107.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.107.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.108.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.108.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.108.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.108.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.109.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.109.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.109.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.109.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.11.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.11.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.11.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.11.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.110.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.110.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.110.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.110.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.111.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.111.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.111.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.111.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.112.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.112.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.112.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.112.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.113.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.113.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.113.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.113.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.114.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.114.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.114.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.114.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.115.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.115.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.115.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.115.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.116.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.116.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.116.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.116.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.117.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.117.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.117.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.117.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.118.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.118.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.118.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.118.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.119.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.119.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.119.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.119.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.12.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.12.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.12.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.12.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.120.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.120.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.120.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.120.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.121.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.121.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.121.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.121.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.122.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.122.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.122.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.122.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.123.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.123.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.123.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.123.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.124.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.124.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.124.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.124.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.125.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.125.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.125.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.125.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.126.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.126.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.126.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.126.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.127.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.127.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.127.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.127.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.13.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.13.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.13.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.13.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.14.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.14.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.14.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.14.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.15.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.15.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.15.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.15.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.16.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.16.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.16.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.16.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.17.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.17.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.17.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.17.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.18.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.18.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.18.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.18.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.19.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.19.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.19.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.19.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.2.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.2.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.2.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.2.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.20.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.20.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.20.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.20.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.21.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.21.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.21.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.21.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.22.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.22.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.22.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.22.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.23.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.23.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.23.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.23.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.24.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.24.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.24.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.24.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.25.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.25.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.25.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.25.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.26.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.26.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.26.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.26.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.27.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.27.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.27.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.27.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.28.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.28.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.28.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.28.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.29.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.29.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.29.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.29.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.3.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.3.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.3.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.3.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.30.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.30.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.30.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.30.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.31.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.31.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.31.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.31.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.32.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.32.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.32.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.32.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.33.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.33.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.33.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.33.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.34.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.34.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.34.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.34.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.35.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.35.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.35.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.35.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.36.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.36.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.36.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.36.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.37.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.37.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.37.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.37.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.38.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.38.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.38.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.38.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.39.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.39.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.39.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.39.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.4.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.4.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.4.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.4.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.40.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.40.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.40.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.40.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.41.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.41.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.41.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.41.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.42.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.42.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.42.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.42.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.43.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.43.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.43.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.43.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.44.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.44.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.44.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.44.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.45.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.45.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.45.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.45.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.46.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.46.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.46.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.46.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.47.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.47.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.47.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.47.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.48.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.48.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.48.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.48.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.49.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.49.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.49.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.49.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.5.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.5.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.5.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.5.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.50.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.50.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.50.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.50.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.51.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.51.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.51.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.51.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.52.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.52.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.52.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.52.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.53.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.53.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.53.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.53.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.54.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.54.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.54.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.54.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.55.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.55.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.55.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.55.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.56.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.56.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.56.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.56.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.57.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.57.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.57.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.57.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.58.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.58.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.58.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.58.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.59.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.59.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.59.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.59.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.6.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.6.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.6.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.6.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.60.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.60.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.60.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.60.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.61.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.61.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.61.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.61.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.62.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.62.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.62.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.62.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.63.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.63.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.63.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.63.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.64.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.64.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.64.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.64.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.65.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.65.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.65.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.65.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.66.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.66.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.66.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.66.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.67.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.67.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.67.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.67.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.68.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.68.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.68.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.68.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.69.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.69.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.69.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.69.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.7.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.7.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.7.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.7.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.70.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.70.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.70.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.70.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.71.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.71.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.71.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.71.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.72.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.72.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.72.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.72.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.73.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.73.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.73.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.73.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.74.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.74.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.74.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.74.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.75.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.75.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.75.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.75.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.76.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.76.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.76.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.76.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.77.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.77.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.77.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.77.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.78.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.78.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.78.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.78.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.79.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.79.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.79.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.79.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.8.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.8.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.8.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.8.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.80.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.80.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.80.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.80.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.81.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.81.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.81.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.81.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.82.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.82.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.82.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.82.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.83.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.83.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.83.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.83.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.84.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.84.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.84.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.84.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.85.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.85.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.85.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.85.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.86.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.86.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.86.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.86.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.87.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.87.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.87.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.87.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.88.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.88.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.88.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.88.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.89.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.89.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.89.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.89.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.9.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.9.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.9.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.9.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.90.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.90.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.90.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.90.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.91.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.91.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.91.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.91.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.92.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.92.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.92.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.92.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.93.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.93.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.93.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.93.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.94.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.94.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.94.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.94.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.95.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.95.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.95.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.95.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.96.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.96.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.96.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.96.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.97.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.97.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.97.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.97.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.98.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.98.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.98.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.98.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.99.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.99.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.99.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.25.mlp.experts.99.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.0.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.1.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.10.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.100.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.101.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.102.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.103.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.104.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.105.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.106.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.107.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.108.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.109.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.11.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.110.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.111.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.112.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.113.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.114.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.115.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.116.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.117.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.118.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.119.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.12.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.120.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.121.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.122.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.123.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.124.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.125.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.126.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.127.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.13.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.14.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.15.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.16.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.17.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.18.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.19.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.2.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.20.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.21.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.22.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.23.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.24.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.25.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.26.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.27.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.28.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.29.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.3.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.30.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.31.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.32.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.33.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.34.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.35.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.36.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.37.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.38.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.39.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.4.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.40.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.41.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.42.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.43.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.44.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.45.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.46.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.47.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.48.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.49.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.5.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.50.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.51.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.52.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.53.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.54.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.55.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.56.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.57.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.58.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.59.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.6.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.60.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.61.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.62.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.63.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.64.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.65.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.66.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.67.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.68.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.69.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.7.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.70.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.71.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.72.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.73.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.74.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.75.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.76.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.77.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.78.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.79.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.8.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.80.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.81.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.82.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.83.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.84.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.85.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.86.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.87.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.88.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.89.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.9.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.90.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.91.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.92.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.93.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.94.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.95.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.96.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.97.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.98.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.experts.99.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.gate.e_score_correction_bias": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.gate.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.shared_experts.down_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.shared_experts.gate_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00028-of-00048.safetensors",
+ "model.layers.26.mlp.shared_experts.up_proj.weight_scale": "model-00028-of-00048.safetensors",
+ "model.layers.21.mlp.experts.0.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.0.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.0.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.0.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.1.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.1.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.1.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.1.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.10.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.10.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.10.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.10.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.100.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.100.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.100.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.100.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.101.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.101.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.101.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.101.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.102.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.102.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.102.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.102.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.103.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.103.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.103.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.103.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.104.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.104.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.104.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.104.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.105.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.105.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.105.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.105.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.106.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.106.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.106.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.106.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.107.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.107.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.107.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.107.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.108.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.108.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.108.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.108.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.109.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.109.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.109.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.109.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.11.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.11.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.11.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.11.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.110.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.110.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.110.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.110.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.111.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.111.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.111.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.111.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.112.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.112.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.112.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.112.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.113.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.113.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.113.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.113.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.114.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.114.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.114.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.114.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.115.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.115.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.115.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.115.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.116.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.116.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.116.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.116.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.117.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.117.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.117.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.117.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.118.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.118.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.118.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.118.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.119.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.119.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.119.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.119.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.12.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.12.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.12.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.12.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.120.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.120.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.120.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.120.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.121.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.121.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.121.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.121.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.122.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.122.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.122.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.122.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.123.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.123.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.123.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.123.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.124.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.124.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.124.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.124.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.125.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.125.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.125.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.125.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.126.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.126.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.126.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.126.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.127.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.127.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.127.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.127.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.13.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.13.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.13.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.13.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.14.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.14.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.14.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.14.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.15.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.15.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.15.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.15.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.16.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.16.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.16.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.16.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.17.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.17.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.17.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.17.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.18.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.18.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.18.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.18.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.19.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.19.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.19.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.19.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.2.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.2.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.2.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.2.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.20.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.20.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.20.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.20.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.21.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.21.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.21.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.21.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.22.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.22.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.22.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.22.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.23.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.23.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.23.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.23.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.24.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.24.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.24.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.24.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.25.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.25.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.25.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.25.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.26.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.26.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.26.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.26.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.27.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.27.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.27.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.27.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.28.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.28.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.28.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.28.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.29.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.29.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.29.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.29.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.3.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.3.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.3.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.3.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.30.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.30.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.30.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.30.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.31.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.31.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.31.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.31.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.32.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.32.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.32.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.32.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.33.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.33.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.33.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.33.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.34.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.34.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.34.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.34.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.35.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.35.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.35.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.35.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.36.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.36.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.36.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.36.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.37.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.37.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.37.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.37.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.38.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.38.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.38.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.38.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.39.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.39.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.39.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.39.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.4.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.4.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.4.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.4.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.40.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.40.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.40.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.40.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.41.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.41.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.41.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.41.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.42.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.42.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.42.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.42.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.43.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.43.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.43.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.43.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.44.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.44.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.44.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.44.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.45.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.45.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.45.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.45.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.46.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.46.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.46.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.46.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.47.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.47.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.47.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.47.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.48.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.48.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.48.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.48.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.49.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.49.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.49.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.49.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.5.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.5.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.5.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.5.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.50.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.50.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.50.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.50.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.51.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.51.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.51.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.51.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.52.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.52.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.52.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.52.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.53.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.53.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.53.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.53.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.54.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.54.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.54.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.54.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.55.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.55.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.55.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.55.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.56.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.56.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.56.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.56.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.57.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.57.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.57.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.57.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.58.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.58.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.58.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.58.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.59.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.59.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.59.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.59.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.6.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.6.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.6.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.6.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.60.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.60.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.60.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.60.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.61.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.61.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.61.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.61.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.62.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.62.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.62.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.62.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.63.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.63.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.63.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.63.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.64.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.64.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.64.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.64.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.65.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.65.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.65.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.65.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.66.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.66.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.66.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.66.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.67.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.67.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.67.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.67.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.68.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.68.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.68.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.68.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.69.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.69.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.69.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.69.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.7.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.7.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.7.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.7.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.70.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.70.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.70.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.70.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.71.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.71.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.71.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.71.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.72.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.72.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.72.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.72.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.73.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.73.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.73.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.73.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.74.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.74.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.74.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.74.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.75.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.75.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.75.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.75.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.76.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.76.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.76.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.76.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.77.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.77.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.77.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.77.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.78.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.78.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.78.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.78.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.79.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.79.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.79.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.79.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.8.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.8.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.8.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.8.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.80.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.80.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.80.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.80.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.81.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.81.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.81.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.81.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.82.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.82.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.82.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.82.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.83.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.83.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.83.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.83.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.84.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.84.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.84.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.84.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.85.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.85.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.85.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.85.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.86.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.86.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.86.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.86.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.87.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.87.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.87.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.87.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.88.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.88.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.88.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.88.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.89.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.89.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.89.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.89.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.9.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.9.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.9.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.9.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.90.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.90.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.90.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.90.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.91.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.91.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.91.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.91.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.92.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.92.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.92.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.92.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.93.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.93.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.93.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.93.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.94.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.94.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.94.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.94.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.95.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.95.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.95.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.95.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.96.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.96.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.96.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.96.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.97.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.97.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.97.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.97.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.98.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.98.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.98.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.98.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.99.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.99.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.99.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.21.mlp.experts.99.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.0.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.1.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.10.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.100.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.101.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.102.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.103.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.104.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.105.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.106.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.107.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.108.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.109.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.11.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.110.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.111.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.112.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.113.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.114.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.115.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.116.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.117.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.118.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.119.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.12.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.120.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.121.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.122.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.123.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.124.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.125.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.126.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.127.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.13.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.14.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.15.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.16.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.17.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.18.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.19.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.2.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.20.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.21.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.22.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.23.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.24.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.25.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.26.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.27.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.28.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.29.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.3.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.30.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.31.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.32.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.33.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.34.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.35.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.36.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.37.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.38.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.39.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.4.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.40.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.41.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.42.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.43.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.44.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.45.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.46.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.47.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.48.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.49.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.5.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.50.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.51.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.52.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.53.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.54.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.55.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.56.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.57.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.58.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.59.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.6.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.60.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.61.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.62.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.63.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.64.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.65.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.66.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.67.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.68.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.69.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.7.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.70.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.71.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.72.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.73.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.74.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.75.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.76.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.77.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.78.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.79.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.8.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.80.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.81.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.82.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.83.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.84.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.85.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.86.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.87.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.88.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.89.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.9.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.90.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.91.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.92.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.93.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.94.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.95.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.96.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.97.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.98.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.experts.99.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.gate.e_score_correction_bias": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.gate.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.shared_experts.down_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.shared_experts.gate_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00024-of-00048.safetensors",
+ "model.layers.22.mlp.shared_experts.up_proj.weight_scale": "model-00024-of-00048.safetensors",
+ "model.layers.10.mlp.experts.0.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.0.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.0.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.0.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.1.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.1.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.1.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.1.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.10.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.10.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.10.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.10.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.100.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.100.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.100.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.100.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.101.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.101.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.101.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.101.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.102.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.102.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.102.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.102.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.103.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.103.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.103.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.103.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.104.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.104.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.104.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.104.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.105.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.105.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.105.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.105.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.106.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.106.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.106.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.106.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.107.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.107.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.107.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.107.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.108.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.108.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.108.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.108.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.109.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.109.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.109.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.109.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.11.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.11.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.11.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.11.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.110.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.110.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.110.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.110.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.111.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.111.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.111.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.111.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.112.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.112.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.112.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.112.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.113.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.113.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.113.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.113.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.114.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.114.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.114.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.114.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.115.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.115.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.115.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.115.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.116.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.116.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.116.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.116.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.117.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.117.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.117.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.117.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.118.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.118.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.118.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.118.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.119.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.119.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.119.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.119.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.12.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.12.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.12.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.12.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.120.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.120.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.120.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.120.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.121.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.121.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.121.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.121.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.122.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.122.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.122.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.122.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.123.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.123.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.123.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.123.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.124.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.124.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.124.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.124.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.125.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.125.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.125.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.125.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.126.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.126.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.126.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.126.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.127.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.127.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.127.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.127.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.13.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.13.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.13.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.13.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.14.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.14.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.14.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.14.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.15.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.15.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.15.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.15.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.16.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.16.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.16.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.16.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.17.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.17.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.17.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.17.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.18.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.18.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.18.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.18.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.19.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.19.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.19.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.19.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.2.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.2.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.2.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.2.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.20.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.20.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.20.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.20.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.21.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.21.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.21.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.21.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.22.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.22.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.22.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.22.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.23.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.23.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.23.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.23.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.24.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.24.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.24.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.24.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.25.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.25.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.25.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.25.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.26.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.26.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.26.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.26.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.27.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.27.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.27.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.27.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.28.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.28.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.28.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.28.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.29.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.29.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.29.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.29.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.3.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.3.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.3.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.3.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.30.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.30.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.30.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.30.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.31.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.31.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.31.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.31.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.32.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.32.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.32.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.32.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.33.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.33.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.33.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.33.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.34.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.34.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.34.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.34.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.35.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.35.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.35.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.35.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.36.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.36.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.36.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.36.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.37.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.37.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.37.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.37.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.38.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.38.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.38.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.38.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.39.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.39.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.39.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.39.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.4.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.4.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.4.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.4.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.40.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.40.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.40.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.40.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.41.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.41.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.41.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.41.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.42.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.42.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.42.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.42.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.43.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.43.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.43.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.43.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.44.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.44.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.44.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.44.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.45.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.45.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.45.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.45.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.46.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.46.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.46.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.46.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.47.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.47.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.47.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.47.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.48.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.48.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.48.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.48.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.49.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.49.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.49.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.49.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.5.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.5.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.5.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.5.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.50.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.50.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.50.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.50.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.51.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.51.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.51.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.51.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.52.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.52.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.52.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.52.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.53.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.53.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.53.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.53.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.54.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.54.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.54.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.54.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.55.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.55.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.55.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.55.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.56.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.56.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.56.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.56.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.57.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.57.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.57.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.57.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.58.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.58.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.58.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.58.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.59.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.59.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.59.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.59.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.6.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.6.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.6.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.6.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.60.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.60.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.60.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.60.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.61.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.61.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.61.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.61.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.62.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.62.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.62.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.62.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.63.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.63.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.63.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.63.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.64.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.64.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.64.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.64.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.65.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.65.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.65.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.65.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.66.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.66.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.66.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.66.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.67.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.67.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.67.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.67.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.68.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.68.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.68.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.68.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.69.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.69.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.69.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.69.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.7.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.7.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.7.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.7.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.70.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.70.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.70.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.70.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.71.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.71.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.71.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.71.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.72.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.72.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.72.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.72.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.73.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.73.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.73.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.73.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.74.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.74.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.74.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.74.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.75.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.75.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.75.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.75.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.76.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.76.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.76.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.76.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.77.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.77.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.77.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.77.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.78.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.78.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.78.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.78.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.79.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.79.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.79.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.79.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.8.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.8.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.8.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.8.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.80.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.80.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.80.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.80.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.81.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.81.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.81.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.81.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.82.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.82.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.82.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.82.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.83.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.83.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.83.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.83.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.84.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.84.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.84.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.84.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.85.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.85.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.85.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.85.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.86.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.86.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.86.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.86.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.87.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.87.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.87.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.87.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.88.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.88.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.88.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.88.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.89.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.89.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.89.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.89.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.9.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.9.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.9.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.9.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.90.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.90.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.90.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.90.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.91.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.91.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.91.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.91.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.92.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.92.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.92.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.92.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.93.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.93.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.93.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.93.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.94.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.94.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.94.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.94.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.95.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.95.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.95.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.95.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.96.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.96.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.96.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.96.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.97.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.97.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.97.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.97.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.98.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.98.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.98.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.98.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.99.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.99.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.99.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.10.mlp.experts.99.up_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.0.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.1.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.10.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.100.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.101.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.102.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.103.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.104.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.105.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.106.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.107.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.108.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.109.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.11.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.110.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.111.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.112.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.113.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.114.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.115.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.116.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.117.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.118.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.119.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.12.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.120.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.121.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.122.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.123.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.124.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.125.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.126.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.127.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.13.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.14.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.15.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.16.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.17.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.18.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.19.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.2.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.20.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.21.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.22.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.23.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.24.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.25.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.26.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.27.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.28.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.29.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.3.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.30.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.31.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.32.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.33.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.34.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.35.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.36.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.37.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.38.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.39.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.4.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.40.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.41.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.42.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.43.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.44.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.45.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.46.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.47.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.48.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.49.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.5.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.50.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.51.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.52.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.53.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.54.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.55.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.56.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.57.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.58.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.59.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.6.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.60.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.61.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.62.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.63.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.64.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.65.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.66.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.67.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.68.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.69.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.7.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.70.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.71.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.72.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.73.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.74.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.75.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.76.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.77.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.78.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.79.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.8.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.80.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.81.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.82.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.83.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.84.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.85.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.86.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.87.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.88.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.89.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.9.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.90.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.91.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.92.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.93.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.94.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.95.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.96.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.97.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.98.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.experts.99.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.gate.e_score_correction_bias": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.gate.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.shared_experts.down_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.shared_experts.gate_proj.weight_scale": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00013-of-00048.safetensors",
+ "model.layers.11.mlp.shared_experts.up_proj.weight_scale": "model-00013-of-00048.safetensors"
+ },
+ "metadata": {
+ "total_size": 83351040
+ }
+}
\ No newline at end of file
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..cef88e33d3754f456782ccbeafee2e549f2270e6
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,40 @@
+{
+ "additional_special_tokens": [
+ "<|endoftext|>",
+ "[MASK]",
+ "[gMASK]",
+ "[sMASK]",
+ "",
+ "",
+ "<|system|>",
+ "<|user|>",
+ "<|assistant|>",
+ "<|observation|>",
+ "<|begin_of_image|>",
+ "<|end_of_image|>",
+ "<|begin_of_video|>",
+ "<|end_of_video|>",
+ "<|begin_of_audio|>",
+ "<|end_of_audio|>",
+ "<|begin_of_transcription|>",
+ "<|end_of_transcription|>",
+ "<|code_prefix|>",
+ "<|code_middle|>",
+ "<|code_suffix|>",
+ "/nothink"
+ ],
+ "eos_token": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ },
+ "pad_token": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false
+ }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..8a090ee6b8bb2f47ede5c58e267ffd79dcdfcbe5
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:840a2be2f18847f07571118fb785c9bde4726991852229d98469e421bf5d1064
+size 19971076
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ec44d0e479c3067a4dd239a69cf6738e3d88c2be
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,341 @@
+{
+ "added_tokens_decoder": {
+ "151329": {
+ "content": "<|endoftext|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151330": {
+ "content": "[MASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151331": {
+ "content": "[gMASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151332": {
+ "content": "[sMASK]",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151333": {
+ "content": "<|im_start|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151334": {
+ "content": "<|im_end|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151335": {
+ "content": "<|system|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151336": {
+ "content": "<|user|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151337": {
+ "content": "<|assistant|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151338": {
+ "content": "<|observation|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151339": {
+ "content": "<|begin_of_image|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151340": {
+ "content": "<|end_of_image|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151341": {
+ "content": "<|begin_of_video|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151342": {
+ "content": "<|end_of_video|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151343": {
+ "content": "<|begin_of_audio|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151344": {
+ "content": "<|end_of_audio|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151345": {
+ "content": "<|begin_of_transcription|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151346": {
+ "content": "<|end_of_transcription|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151347": {
+ "content": "<|code_prefix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151348": {
+ "content": "<|code_middle|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151349": {
+ "content": "<|code_suffix|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151350": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151351": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151352": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151353": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151354": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151355": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151356": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151357": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151358": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151359": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151360": {
+ "content": "/nothink",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151361": {
+ "content": "<|begin_of_box|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151362": {
+ "content": "<|end_of_box|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151363": {
+ "content": "<|image|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151364": {
+ "content": "<|video|>",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": false
+ },
+ "151365": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ },
+ "151366": {
+ "content": "",
+ "lstrip": false,
+ "normalized": false,
+ "rstrip": false,
+ "single_word": false,
+ "special": true
+ }
+ },
+ "additional_special_tokens": [
+ "<|endoftext|>",
+ "[MASK]",
+ "[gMASK]",
+ "[sMASK]",
+ "",
+ "",
+ "<|system|>",
+ "<|user|>",
+ "<|assistant|>",
+ "<|observation|>",
+ "<|begin_of_image|>",
+ "<|end_of_image|>",
+ "<|begin_of_video|>",
+ "<|end_of_video|>",
+ "<|begin_of_audio|>",
+ "<|end_of_audio|>",
+ "<|begin_of_transcription|>",
+ "<|end_of_transcription|>",
+ "<|code_prefix|>",
+ "<|code_middle|>",
+ "<|code_suffix|>",
+ "/nothink"
+ ],
+ "clean_up_tokenization_spaces": false,
+ "do_lower_case": false,
+ "eos_token": "<|im_end|>",
+ "extra_special_tokens": {},
+ "model_max_length": 128000,
+ "pad_token": "<|endoftext|>",
+ "padding_side": "left",
+ "remove_space": false,
+ "tokenizer_class": "PreTrainedTokenizerFast"
+}