diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..aa7aacd0134a92c3c1943fdecc75cd8b7420cce6 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,5 @@ 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
+model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/README.md b/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/chat_template.jinja b/chat_template.jinja
new file mode 100644
index 0000000000000000000000000000000000000000..a585dec894e63da457d9440ec6aa7caa16d20860
--- /dev/null
+++ b/chat_template.jinja
@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+ {%- if content is string %}
+ {{- content }}
+ {%- elif content is iterable and content is not mapping %}
+ {%- for item in content %}
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+ {%- if is_system_content %}
+ {{- raise_exception('System message cannot contain images.') }}
+ {%- endif %}
+ {%- if do_vision_count %}
+ {%- set image_count.value = image_count.value + 1 %}
+ {%- endif %}
+ {%- if add_vision_id %}
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
+ {%- endif %}
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+ {%- elif 'video' in item or item.type == 'video' %}
+ {%- if is_system_content %}
+ {{- raise_exception('System message cannot contain videos.') }}
+ {%- endif %}
+ {%- if do_vision_count %}
+ {%- set video_count.value = video_count.value + 1 %}
+ {%- endif %}
+ {%- if add_vision_id %}
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
+ {%- endif %}
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+ {%- elif 'text' in item %}
+ {{- item.text }}
+ {%- else %}
+ {{- raise_exception('Unexpected item type in content.') }}
+ {%- endif %}
+ {%- endfor %}
+ {%- elif content is none or content is undefined %}
+ {{- '' }}
+ {%- else %}
+ {{- raise_exception('Unexpected content type.') }}
+ {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+ {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+ {{- '<|im_start|>system\n' }}
+ {{- "# Tools\n\nYou have access to the following functions:\n\n" }}
+ {%- for tool in tools %}
+ {{- "\n" }}
+ {{- tool | tojson }}
+ {%- 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' }}
+ {%- if messages[0].role == 'system' %}
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
+ {%- if content %}
+ {{- '\n\n' + content }}
+ {%- endif %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+{%- else %}
+ {%- if messages[0].role == 'system' %}
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+ {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+ {%- set index = (messages|length - 1) - loop.index0 %}
+ {%- if ns.multi_step_tool and message.role == "user" %}
+ {%- set content = render_content(message.content, false)|trim %}
+ {%- if not(content.startswith('') and content.endswith('')) %}
+ {%- set ns.multi_step_tool = false %}
+ {%- set ns.last_query_index = index %}
+ {%- endif %}
+ {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+ {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+ {%- set content = render_content(message.content, true)|trim %}
+ {%- if message.role == "system" %}
+ {%- if not loop.first %}
+ {{- raise_exception('System message must be at the beginning.') }}
+ {%- endif %}
+ {%- elif message.role == "user" %}
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+ {%- elif message.role == "assistant" %}
+ {%- set reasoning_content = '' %}
+ {%- if message.reasoning_content is string %}
+ {%- set reasoning_content = message.reasoning_content %}
+ {%- else %}
+ {%- if '' in content %}
+ {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %}
+ {%- set content = content.split('')[-1].lstrip('\n') %}
+ {%- endif %}
+ {%- endif %}
+ {%- set reasoning_content = reasoning_content|trim %}
+ {%- if loop.index0 > ns.last_query_index %}
+ {{- '<|im_start|>' + message.role + '\n\n' + reasoning_content + '\n\n\n' + content }}
+ {%- else %}
+ {{- '<|im_start|>' + message.role + '\n' + content }}
+ {%- endif %}
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+ {%- for tool_call in message.tool_calls %}
+ {%- if tool_call.function is defined %}
+ {%- set tool_call = tool_call.function %}
+ {%- endif %}
+ {%- if loop.first %}
+ {%- if content|trim %}
+ {{- '\n\n\n\n' }}
+ {%- else %}
+ {{- '\n\n' }}
+ {%- endif %}
+ {%- else %}
+ {{- '\n\n\n' }}
+ {%- endif %}
+ {%- 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 %}
+ {%- endif %}
+ {{- '<|im_end|>\n' }}
+ {%- elif message.role == "tool" %}
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
+ {{- '<|im_start|>user' }}
+ {%- endif %}
+ {{- '\n\n' }}
+ {{- content }}
+ {{- '\n' }}
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
+ {{- '<|im_end|>\n' }}
+ {%- elif loop.last %}
+ {{- '<|im_end|>\n' }}
+ {%- endif %}
+ {%- else %}
+ {{- raise_exception('Unexpected message role.') }}
+ {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+ {{- '<|im_start|>assistant\n' }}
+ {%- if enable_thinking is defined and enable_thinking is false %}
+ {{- '\n\n\n\n' }}
+ {%- else %}
+ {{- '\n' }}
+ {%- endif %}
+{%- endif %}
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..8816d1fbf12c53408f327bc21379b741f700525d
--- /dev/null
+++ b/config.json
@@ -0,0 +1,1790 @@
+{
+ "architectures": [
+ "Qwen3_5MoeForConditionalGeneration"
+ ],
+ "dtype": "bfloat16",
+ "image_token_id": 248056,
+ "model_type": "qwen3_5_moe",
+ "quantization_config": {
+ "autoround_version": "0.12.0",
+ "bits": 4,
+ "block_name_to_quantize": "model.language_model.layers",
+ "data_type": "int",
+ "extra_config": {
+ "model.language_model.layers.0.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.1.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.10.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.11.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.11.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.11.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.11.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.11.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.11.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.11.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.11.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.13.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.14.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.15.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.15.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.15.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.15.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.15.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.15.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.15.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.15.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.17.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.18.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.19.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.19.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.19.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.19.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.19.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.19.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.19.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.19.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.20.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.21.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.22.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.23.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.23.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.23.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.23.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.23.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.23.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.23.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.23.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.25.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.26.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.27.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.27.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.27.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.27.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.27.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.27.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.27.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.27.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.29.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.3.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.3.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.3.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.3.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.3.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.3.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.3.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.3.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.31.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.31.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.31.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.31.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.31.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.31.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.31.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.31.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.33.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.34.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.35.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.35.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.35.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.35.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.35.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.35.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.35.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.35.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.37.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.38.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.39.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.39.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.39.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.39.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.39.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.39.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.39.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.39.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.40.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.41.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.42.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.43.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.43.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.43.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.43.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.43.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.43.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.43.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.43.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.45.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.46.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.47.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.47.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.47.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.47.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.47.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.47.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.47.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.47.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.49.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.5.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.50.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.51.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.51.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.51.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.51.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.51.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.51.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.51.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.51.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.53.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.54.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.55.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.55.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.55.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.55.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.55.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.55.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.55.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.55.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.57.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.58.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.59.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.59.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.59.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.59.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.59.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.59.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.59.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.59.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.7.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.7.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.7.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.7.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.7.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.7.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.7.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.7.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.9.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ }
+ },
+ "group_size": 128,
+ "iters": 0,
+ "packing_format": "auto_round:auto_gptq",
+ "quant_method": "auto-round",
+ "sym": true
+ },
+ "text_config": {
+ "attention_bias": false,
+ "attention_dropout": 0.0,
+ "attn_output_gate": true,
+ "bos_token_id": null,
+ "dtype": "bfloat16",
+ "eos_token_id": 248044,
+ "full_attention_interval": 4,
+ "head_dim": 256,
+ "hidden_act": "silu",
+ "hidden_size": 4096,
+ "initializer_range": 0.02,
+ "layer_types": [
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention",
+ "linear_attention",
+ "linear_attention",
+ "linear_attention",
+ "full_attention"
+ ],
+ "linear_conv_kernel_dim": 4,
+ "linear_key_head_dim": 128,
+ "linear_num_key_heads": 16,
+ "linear_num_value_heads": 64,
+ "linear_value_head_dim": 128,
+ "mamba_ssm_dtype": "float32",
+ "max_position_embeddings": 262144,
+ "mlp_only_layers": [],
+ "model_type": "qwen3_5_moe_text",
+ "moe_intermediate_size": 1024,
+ "mtp_num_hidden_layers": 1,
+ "mtp_use_dedicated_embeddings": false,
+ "num_attention_heads": 32,
+ "num_experts": 512,
+ "num_experts_per_tok": 10,
+ "num_hidden_layers": 60,
+ "num_key_value_heads": 2,
+ "output_router_logits": false,
+ "pad_token_id": null,
+ "partial_rotary_factor": 0.25,
+ "rms_norm_eps": 1e-06,
+ "rope_parameters": {
+ "mrope_interleaved": true,
+ "mrope_section": [
+ 11,
+ 11,
+ 10
+ ],
+ "partial_rotary_factor": 0.25,
+ "rope_theta": 10000000,
+ "rope_type": "default"
+ },
+ "router_aux_loss_coef": 0.001,
+ "shared_expert_intermediate_size": 1024,
+ "tie_word_embeddings": false,
+ "use_cache": true,
+ "vocab_size": 248320
+ },
+ "tie_word_embeddings": false,
+ "transformers_version": "5.2.0.dev0",
+ "video_token_id": 248057,
+ "vision_config": {
+ "deepstack_visual_indexes": [],
+ "depth": 27,
+ "dtype": "bfloat16",
+ "hidden_act": "gelu_pytorch_tanh",
+ "hidden_size": 1152,
+ "in_channels": 3,
+ "initializer_range": 0.02,
+ "intermediate_size": 4304,
+ "model_type": "qwen3_5_moe",
+ "num_heads": 16,
+ "num_position_embeddings": 2304,
+ "out_hidden_size": 4096,
+ "patch_size": 16,
+ "spatial_merge_size": 2,
+ "temporal_patch_size": 2
+ },
+ "vision_end_token_id": 248054,
+ "vision_start_token_id": 248053
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..9a2baed1f4216aebb495d5fe75b556945077d8c9
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,13 @@
+{
+ "bos_token_id": 248044,
+ "do_sample": true,
+ "eos_token_id": [
+ 248046,
+ 248044
+ ],
+ "pad_token_id": 248044,
+ "temperature": 0.6,
+ "top_k": 20,
+ "top_p": 0.95,
+ "transformers_version": "5.2.0.dev0"
+}
diff --git a/model-00001-of-00042.safetensors b/model-00001-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a5a4bc85d8759037bab12bd0099460eee7392e65
--- /dev/null
+++ b/model-00001-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d944ceff89c5b2042e42f3e66e3f69659b92d2f0fee203f5fcfcd26089d2c46
+size 5365497040
diff --git a/model-00002-of-00042.safetensors b/model-00002-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..edf7c6c208929111a4f42e0d138759c6a37a2dba
--- /dev/null
+++ b/model-00002-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8977801d9fe53b5f5b5a6eaeb383ff8d136eaaa5da5980e29605696b7aa9c4fe
+size 5365599616
diff --git a/model-00003-of-00042.safetensors b/model-00003-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a7f4077d7c07124635e509752bcba8c78b36bc5d
--- /dev/null
+++ b/model-00003-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a10d5067ac8cc1e0a0efab2ff2d94c00c5c4d6783bd6c1a3d533371851e9bd
+size 5367720344
diff --git a/model-00004-of-00042.safetensors b/model-00004-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3f144dd2412eb9d52e2a62b9b93b51ba676938d4
--- /dev/null
+++ b/model-00004-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e3bb27e8d25982d9bfaa359e12c8a2190475e05d36f03c3932cdf7e5b3e1bdd
+size 5367735216
diff --git a/model-00005-of-00042.safetensors b/model-00005-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7e9c99c588685ec6c19ff26ef73e61894b840aca
--- /dev/null
+++ b/model-00005-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a23693952202ef73810c173b56b6fd1dc1d38877622cef7dc08a7c1e0a650b61
+size 5365599880
diff --git a/model-00006-of-00042.safetensors b/model-00006-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1d2c24036e8e707f5088b21d848f349f134e4e40
--- /dev/null
+++ b/model-00006-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eeb1dc1ffdfa6f1742d943da81330c65012ebb43d614437b9207b00e368b4c1
+size 5365497104
diff --git a/model-00007-of-00042.safetensors b/model-00007-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..934564a0a5fa9618c3037a3a6e9bad748ac1fc9d
--- /dev/null
+++ b/model-00007-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a67c0697b7f7c26f04a570b5ac7100c9a39b3b02ddbaa529fc3791d2836908
+size 5365603200
diff --git a/model-00008-of-00042.safetensors b/model-00008-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..95b0f4405bf568c05b4061d7ed77aab687ef276c
--- /dev/null
+++ b/model-00008-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8bec9f64a77783347e3a0f34cceb0da25f3b51eea0383f79c2618efe491f8e
+size 5367729992
diff --git a/model-00009-of-00042.safetensors b/model-00009-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5a930b0e7730f583eaa73237fbe8a3f5f1738a5f
--- /dev/null
+++ b/model-00009-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:555e618cb1a4fb561e7776a7a33ec3ddbd44e3f8dcc1c54e1578404908284843
+size 5367735256
diff --git a/model-00010-of-00042.safetensors b/model-00010-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..579e544cbd723ccf6cf5ee278300fe2c72bce3a9
--- /dev/null
+++ b/model-00010-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c907d2aaed1af1987b9fdce179a55511ef3f2db4ed70967d7f1a433f53cc93d
+size 5365605080
diff --git a/model-00011-of-00042.safetensors b/model-00011-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..df7857e0271ebd8b1a506bef9a88850e5bc88c72
--- /dev/null
+++ b/model-00011-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43042c370b68366326b20d06dc7549b6e710aeeb6b3ffc1d362c6222bd7118d1
+size 5365501600
diff --git a/model-00012-of-00042.safetensors b/model-00012-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7fc1657f8c618276eecfe35d0342a95f5db16f1d
--- /dev/null
+++ b/model-00012-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dea2b9859c09f437502d6509cd80f646ced0cc2ba8a6e61e23a5823cca3a6ebe
+size 5365604848
diff --git a/model-00013-of-00042.safetensors b/model-00013-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c465057e926f0662d575329004e9a565adfb9704
--- /dev/null
+++ b/model-00013-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd177605ee8e2678b26840283d133a05865946cb15b55f7dc70e8391dcc4ee2
+size 5367734848
diff --git a/model-00014-of-00042.safetensors b/model-00014-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fe51df9bb653e0472063054b2ff625bc8e9c2a07
--- /dev/null
+++ b/model-00014-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82eb0b5bbaa318b2bee81e310f0fbc7f5a0a9866d194e4fb6b47027c4bda1eca
+size 5367730400
diff --git a/model-00015-of-00042.safetensors b/model-00015-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..63ac50c0341aeb4c4eaba0a4a2e2a8212001d37f
--- /dev/null
+++ b/model-00015-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3301a2e7cc7dd587059081394f43f97a57685922109479c7a2ff5022877bd346
+size 5365605040
diff --git a/model-00016-of-00042.safetensors b/model-00016-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ae7727c3e12bfebd261ac1b83f2e9248d0538e5c
--- /dev/null
+++ b/model-00016-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80f77b8fc30183c0f1362f522769158e67601571a1b6d138092f3502d9676890
+size 5365501640
diff --git a/model-00017-of-00042.safetensors b/model-00017-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8cf10fc21cc2c140d128db88fae7f49849319b66
--- /dev/null
+++ b/model-00017-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca69c79f539cb56dd384d568b994dcee6f50faf9d11e684832877122e3aa564
+size 5365604848
diff --git a/model-00018-of-00042.safetensors b/model-00018-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7824b763b87e53a4517921e1c7caf851ebab42d5
--- /dev/null
+++ b/model-00018-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e1911e111d74a33aa3e0ae7e42f3a1f042b0d92d9b1b19af4101dece83aa098
+size 5367739712
diff --git a/model-00019-of-00042.safetensors b/model-00019-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ca8902e88f00ca005d7462fed554bb24eb973532
--- /dev/null
+++ b/model-00019-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:883e8a16df4dd0382372bde5db2437deb9019266232bb70a8b4c522d2fea35de
+size 5367725536
diff --git a/model-00020-of-00042.safetensors b/model-00020-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..caa2e7db3fcdcc331eba479700d7148bdbe21f7d
--- /dev/null
+++ b/model-00020-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a166e5497e8426e5e83bd8b2a0f46fd119127c06285599c5068375b02a099cf
+size 5365605008
diff --git a/model-00021-of-00042.safetensors b/model-00021-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..346a871df5932248997c209635f4759c63fdd790
--- /dev/null
+++ b/model-00021-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba53c94e68167c8be47722e74f85a467eaa973a348725e872b56d6575059d73e
+size 5365501672
diff --git a/model-00022-of-00042.safetensors b/model-00022-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b821193a78a598186fcb2d2c0750897e76cd2219
--- /dev/null
+++ b/model-00022-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:972f698fe22b7e266ebaef1a8fed8f0efa63839f6308791a118da40fb28eef4b
+size 5365604848
diff --git a/model-00023-of-00042.safetensors b/model-00023-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..dd9f99a6cbf577f08ad6998be6c20292663c6d1a
--- /dev/null
+++ b/model-00023-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9f646e88b93784419b3c9fb0215c5899d42fe797e52b26d40159dee667c4ca4
+size 5367744568
diff --git a/model-00024-of-00042.safetensors b/model-00024-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e7ced08194f8f021f91e64b1b350bc453e56eaf5
--- /dev/null
+++ b/model-00024-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4abb0dd746af8fa94ab0b9afea61f73d408b0d19e0b74580f9676bec31c7e4b9
+size 5367720680
diff --git a/model-00025-of-00042.safetensors b/model-00025-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..dad1da9afe133c3d28d331d7c2c7d079fcfb4f9a
--- /dev/null
+++ b/model-00025-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4990f080f99500e92402593c42159a78a10bdb8b1b72a398da62b46159a2dbd
+size 5365604968
diff --git a/model-00026-of-00042.safetensors b/model-00026-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6278caa066b5e1d0264998d0e3e1d15829e4b109
--- /dev/null
+++ b/model-00026-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1050dcd3dedc7029dacbf844e87a181c5afd83fa18309d83415646b755506fd
+size 5367685552
diff --git a/model-00027-of-00042.safetensors b/model-00027-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..10198aed954403a080eb83f6803a668e9a931ccc
--- /dev/null
+++ b/model-00027-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57067853385ead56408bdd4f1bc06fbb31d67a2e868e6044d6c98948917eb52a
+size 5367779576
diff --git a/model-00028-of-00042.safetensors b/model-00028-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d1c6b7b696ed142bc8d9b778c44b205e219c91cc
--- /dev/null
+++ b/model-00028-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09d1103347f2f1fa45f9431f826f5a4a2566c9a9180b40bb82e0977304328a2
+size 5367749840
diff --git a/model-00029-of-00042.safetensors b/model-00029-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c5bee52002aa18da378fc0215824ac8dd0676d8b
--- /dev/null
+++ b/model-00029-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e7b97b4b73c47018eb1dec8c40ea029558a3ba8b321a5e37ddcac1145794ed
+size 5367715408
diff --git a/model-00030-of-00042.safetensors b/model-00030-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..efa2ac66318f2048344784a39312703d6a5f7024
--- /dev/null
+++ b/model-00030-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b81f76175dc20a8f1e40411340d88db8dfb3a6085c14e307b001ac9db69ddf
+size 5365604928
diff --git a/model-00031-of-00042.safetensors b/model-00031-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..522e07b1fb0c9df5896deb2aba6d1f7efd384b2f
--- /dev/null
+++ b/model-00031-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8df7e13d7be5b53af0986aac3378e5fd19673dcb4db3c334154691f0210c41a
+size 5367690776
diff --git a/model-00032-of-00042.safetensors b/model-00032-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..911ae39638ae3a70a840e0e68f80a7af1e7516ae
--- /dev/null
+++ b/model-00032-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c99e8eea00cb6b0b41833bdb01308c2d008fc63bc3179cda859a6c26c5015497
+size 5367774392
diff --git a/model-00033-of-00042.safetensors b/model-00033-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..015ef2046ee95320173cb2fb5ed81745692473db
--- /dev/null
+++ b/model-00033-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eac007b8e3db6ab7af09c4c4569187382325fb4112653f2e0d3c6c495603c3e
+size 5367755104
diff --git a/model-00034-of-00042.safetensors b/model-00034-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f6b951baf9c297cf14fe4546391a123f87b576cb
--- /dev/null
+++ b/model-00034-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15349bef8ebb1c1ca6b54ca9aa66de827fff1d7f9ced85fd708091c660a08cde
+size 5367710144
diff --git a/model-00035-of-00042.safetensors b/model-00035-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..988a63ec94547438b2969bb82bd59151a22d201a
--- /dev/null
+++ b/model-00035-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b526974130894dec47d6c06c10791445719c58341219124dc651e01d71705a59
+size 5365604888
diff --git a/model-00036-of-00042.safetensors b/model-00036-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..bc03cdabf09d668a5e076cec8162dc3e5f3c80a9
--- /dev/null
+++ b/model-00036-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce8737d93c6dabe161576e076f13e212194cef5b87ff72753345375330c2612
+size 5367696008
diff --git a/model-00037-of-00042.safetensors b/model-00037-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..861ef89ec756f412004a0dfce4102dcf29e2ccb8
--- /dev/null
+++ b/model-00037-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a9fc56b924b355ed5a8b4d9adf701b635a5cd67de6a683970580e202eb2e2b
+size 5367769200
diff --git a/model-00038-of-00042.safetensors b/model-00038-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..768bfa910fe48c6256d30201bf87b30571b00840
--- /dev/null
+++ b/model-00038-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd0e35b8ca2c3de8d1506a5081e2e30370ba8e7bfbeb1abd636cfa69a68e4da1
+size 5293138480
diff --git a/model-00039-of-00042.safetensors b/model-00039-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..96f4167432fa46e8be70314d3d4b1d0a5fcac655
--- /dev/null
+++ b/model-00039-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ba8109aa58e767a9daa7ff723da5844a8bcbbb69f55f660e9982d7f3fd1d657
+size 5366535232
diff --git a/model-00040-of-00042.safetensors b/model-00040-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5aaeffd1667c1b65a80de9e79d5293964b5bc0b0
--- /dev/null
+++ b/model-00040-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0df10a8586dcd1326c5a5d9c9e19123550a8488f358a80bacc9e9c8ee913eb11
+size 5353027632
diff --git a/model-00041-of-00042.safetensors b/model-00041-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..2887e953faaed0e4182cae79a5c2ac51a2da19b4
--- /dev/null
+++ b/model-00041-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8fe02a3f59ecc352ee5ea064f34d837c8e20732088eb314af16e0a1abcf90ae
+size 5367690384
diff --git a/model-00042-of-00042.safetensors b/model-00042-of-00042.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..866c0c4003a41da4e44a5376728a55af791ed339
--- /dev/null
+++ b/model-00042-of-00042.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aa9ba6946cd0767a9e5113b85ec878fa02fdae13169d2f6c64e37f0a15d2d31
+size 3689643872
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000000000000000000000000000000000000..c9c76c9f56f766ebe3d2b5d3e75d54c967e7715a
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61432fba053c3c2436c1224f68ff19bdfc78c0ebea6310747061b959d8d05ae1
+size 20109911
diff --git a/processor_config.json b/processor_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..7ad6acdf4203f22b7b990e36ccc3a1fe38563d5e
--- /dev/null
+++ b/processor_config.json
@@ -0,0 +1,63 @@
+{
+ "image_processor": {
+ "data_format": "channels_first",
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_processor_type": "Qwen2VLImageProcessorFast",
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "merge_size": 2,
+ "patch_size": 16,
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "size": {
+ "longest_edge": 16777216,
+ "shortest_edge": 65536
+ },
+ "temporal_patch_size": 2
+ },
+ "processor_class": "Qwen3VLProcessor",
+ "video_processor": {
+ "data_format": "channels_first",
+ "default_to_square": true,
+ "do_convert_rgb": true,
+ "do_normalize": true,
+ "do_rescale": true,
+ "do_resize": true,
+ "do_sample_frames": true,
+ "fps": 2,
+ "image_mean": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "image_std": [
+ 0.5,
+ 0.5,
+ 0.5
+ ],
+ "max_frames": 768,
+ "merge_size": 2,
+ "min_frames": 4,
+ "patch_size": 16,
+ "resample": 3,
+ "rescale_factor": 0.00392156862745098,
+ "return_metadata": false,
+ "size": {
+ "longest_edge": 25165824,
+ "shortest_edge": 4096
+ },
+ "temporal_patch_size": 2,
+ "video_processor_type": "Qwen3VLVideoProcessor"
+ }
+}
diff --git a/quantization_config.json b/quantization_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..4854a1645ddfccb2407e5fc31672723dbbf297ed
--- /dev/null
+++ b/quantization_config.json
@@ -0,0 +1,1648 @@
+{
+ "bits": 4,
+ "data_type": "int",
+ "group_size": 128,
+ "sym": true,
+ "iters": 0,
+ "autoround_version": "0.12.0",
+ "block_name_to_quantize": "model.language_model.layers",
+ "quant_method": "auto-round",
+ "packing_format": "auto_round:auto_gptq",
+ "extra_config": {
+ "model.language_model.layers.0.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.1.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.2.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.3.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.4.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.5.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.6.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.7.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.8.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.9.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.10.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.11.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.12.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.13.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.14.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.15.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.16.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.17.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.18.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.19.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.20.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.21.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.22.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.23.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.24.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.25.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.26.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.27.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.28.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.29.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.30.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.31.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.32.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.33.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.34.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.35.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.36.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.37.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.38.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.39.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.40.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.41.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.42.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.43.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.44.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.45.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.46.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.47.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.48.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.49.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.50.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.51.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.52.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.53.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.54.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.55.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.56.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.57.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.58.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.59.mlp.shared_expert_gate": {
+ "bits": 16,
+ "data_type": "fp"
+ },
+ "model.language_model.layers.0.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.0.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.1.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.2.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.3.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.3.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.3.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.3.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.3.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.3.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.3.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.4.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.5.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.6.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.7.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.7.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.7.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.7.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.7.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.7.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.7.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.8.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.9.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.10.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.11.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.11.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.11.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.11.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.11.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.11.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.11.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.12.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.13.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.14.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.15.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.15.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.15.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.15.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.15.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.15.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.15.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.16.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.17.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.18.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.19.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.19.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.19.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.19.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.19.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.19.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.19.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.20.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.21.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.22.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.23.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.23.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.23.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.23.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.23.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.23.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.23.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.24.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.25.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.26.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.27.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.27.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.27.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.27.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.27.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.27.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.27.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.28.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.29.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.30.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.31.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.31.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.31.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.31.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.31.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.31.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.31.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.32.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.33.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.34.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.35.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.35.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.35.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.35.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.35.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.35.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.35.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.36.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.37.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.38.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.39.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.39.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.39.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.39.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.39.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.39.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.39.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.40.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.41.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.42.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.43.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.43.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.43.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.43.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.43.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.43.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.43.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.44.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.45.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.46.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.47.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.47.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.47.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.47.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.47.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.47.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.47.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.48.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.49.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.50.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.51.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.51.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.51.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.51.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.51.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.51.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.51.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.52.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.53.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.54.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.55.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.55.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.55.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.55.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.55.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.55.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.55.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.56.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.57.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.linear_attn.out_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.linear_attn.in_proj_qkv": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.linear_attn.in_proj_z": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.linear_attn.in_proj_b": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.linear_attn.in_proj_a": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.58.mlp.shared_expert.down_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.59.self_attn.q_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.59.self_attn.k_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.59.self_attn.v_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.59.self_attn.o_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.59.mlp.shared_expert.gate_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.59.mlp.shared_expert.up_proj": {
+ "bits": 16
+ },
+ "model.language_model.layers.59.mlp.shared_expert.down_proj": {
+ "bits": 16
+ }
+ }
+}
\ No newline at end of file
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..67741b04f23bfdb46501f748ce27865ec82eccfb
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
+size 19989343
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..541f6c47f2feadecb8b5e1381446e252f4054e8d
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,32 @@
+{
+ "add_prefix_space": false,
+ "audio_bos_token": "<|audio_start|>",
+ "audio_eos_token": "<|audio_end|>",
+ "audio_token": "<|audio_pad|>",
+ "backend": "tokenizers",
+ "bos_token": null,
+ "clean_up_tokenization_spaces": false,
+ "eos_token": "<|im_end|>",
+ "errors": "replace",
+ "image_token": "<|image_pad|>",
+ "is_local": false,
+ "model_max_length": 262144,
+ "model_specific_special_tokens": {
+ "audio_bos_token": "<|audio_start|>",
+ "audio_eos_token": "<|audio_end|>",
+ "audio_token": "<|audio_pad|>",
+ "image_token": "<|image_pad|>",
+ "video_token": "<|video_pad|>",
+ "vision_bos_token": "<|vision_start|>",
+ "vision_eos_token": "<|vision_end|>"
+ },
+ "pad_token": "<|endoftext|>",
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+ "processor_class": "Qwen3VLProcessor",
+ "split_special_tokens": false,
+ "tokenizer_class": "TokenizersBackend",
+ "unk_token": null,
+ "video_token": "<|video_pad|>",
+ "vision_bos_token": "<|vision_start|>",
+ "vision_eos_token": "<|vision_end|>"
+}