diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000000000000000000000000000000000000..52373fe24473b1aa44333d318f578ae6bf04b49b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/NCCL_READY b/NCCL_READY new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..d931e8443654bd599e4ee5c452b7a57182e5d66b --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +library_name: transformers +tags: +- prime-rl +- verifiers +- prime-intellect +- reinforcement-learning +- reasoning +- agentic +- mixture-of-experts +license: mit +language: +- en +base_model: +- zai-org/GLM-4.5-Air-Base +pipeline_tag: text-generation +--- + +# INTELLECT-3.1 + +
+Prime Intellect Logo +
+ +

+ INTELLECT-3.1: A 100B+ MoE trained with large-scale RL +

+ Trained with prime-rl and verifiers +
+ Environments released on Environments Hub +
+ Read the Blog & Technical Report +
+ X | Discord | Prime Intellect Platform +

+ +## Introduction + +**INTELLECT-3.1** is a 106B (A12B) parameter Mixture-of-Experts reasoning model built as a continued training of [INTELLECT-3](https://huggingface.co/PrimeIntellect/INTELLECT-3) with additional reinforcement learning on math, coding, software engineering, and agentic tasks. + +Training was performed with [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl) using environments built with the [verifiers](https://github.com/PrimeIntellect-ai/verifiers) library. +All training and evaluation environments are available on the [Environments Hub](https://app.primeintellect.ai/dashboard/environments). + +The model, training frameworks, and environments are open-sourced under fully-permissive licenses (MIT and Apache 2.0). + +For more details, see the [technical report](https://storage.googleapis.com/intellect-3-paper/INTELLECT_3_Technical_Report.pdf). + +## Serving with vLLM + +The model can be served on 2x H200s: +```bash +vllm serve PrimeIntellect/INTELLECT-3.1 \ + --tensor-parallel-size 2 \ + --enable-auto-tool-choice \ + --tool-call-parser qwen3_coder \ + --reasoning-parser deepseek_r1 +``` + +## Citation + +```bibtex +@misc{intellect3.1, + title={INTELLECT-3.1: Technical Report}, + author={Prime Intellect Team}, + year={2025}, + url={https://huggingface.co/PrimeIntellect/INTELLECT-3.1} +} +``` diff --git a/STABLE b/STABLE new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/banner.png b/banner.png new file mode 100644 index 0000000000000000000000000000000000000000..dd4ee9ad2e48290be31b429bcae7db8e8d0b40c9 Binary files /dev/null and b/banner.png differ diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..33a118a8cb8f6511727b23c9b4201bbee2e94205 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,137 @@ +{% macro render_extra_keys(json_dict, handled_keys) %} + {%- if json_dict is mapping %} + {%- for json_key in json_dict if json_key not in handled_keys %} + {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %} + {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '' }} + {%- else %} + {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '' }} + {%- endif %} + {%- endfor %} + {%- endif %} +{% endmacro %} + +{%- if messages[0]["role"] == "system" %} + {%- set system_message = messages[0]["content"] %} + {%- set loop_messages = messages[1:] %} +{%- else %} + {%- set loop_messages = messages %} +{%- endif %} + +{%- if not tools is defined %} + {%- set tools = [] %} +{%- endif %} + +{%- if system_message is defined %} + {{- "<|im_start|>system\n" + system_message }} +{%- else %} + {%- if tools is iterable and tools | length > 0 %} + {{- "<|im_start|>system\nYou are INTELLECT-4, a helpful assistant developed by Prime Intellect, that can interact with a computer to solve tasks." }} + {%- endif %} +{%- endif %} +{%- if tools is iterable and tools | length > 0 %} + {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }} + {{- "" }} + {%- for tool in tools %} + {%- if tool.function is defined %} + {%- set tool = tool.function %} + {%- endif %} + {{- "\n\n" ~ tool.name ~ "" }} + {%- if tool.description is defined %} + {{- '\n' ~ (tool.description | trim) ~ '' }} + {%- endif %} + {{- '\n' }} + {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %} + {%- for param_name, param_fields in tool.parameters.properties|items %} + {{- '\n' }} + {{- '\n' ~ param_name ~ '' }} + {%- if param_fields.type is defined %} + {{- '\n' ~ (param_fields.type | string) ~ '' }} + {%- endif %} + {%- if param_fields.description is defined %} + {{- '\n' ~ (param_fields.description | trim) ~ '' }} + {%- endif %} + {%- set handled_keys = ['name', 'type', 'description'] %} + {{- render_extra_keys(param_fields, handled_keys) }} + {{- '\n' }} + {%- endfor %} + {%- endif %} + {% set handled_keys = ['type', 'properties'] %} + {{- render_extra_keys(tool.parameters, handled_keys) }} + {{- '\n' }} + {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %} + {{- render_extra_keys(tool, handled_keys) }} + {{- '\n' }} + {%- endfor %} + {{- "\n" }} + {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }} +{%- endif %} +{%- if system_message is defined %} + {{- '<|im_end|>\n' }} +{%- else %} + {%- if tools is iterable and tools | length > 0 %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in loop_messages %} + {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %} + {{- '<|im_start|>' + message.role }} + {%- if message.content is defined and message.content is string %} + {%- if message.reasoning_content is defined -%} + {%- if message.reasoning_content -%} + {{ '\n' + message.reasoning_content.strip() + '' }} + {%- else -%} + {{ '\n' }} + {%- endif -%} + {%- endif -%} + {{- '\n' + message.content | trim + '\n' }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n\n' }} + {%- if tool_call.arguments is defined %} + {%- for args_name, args_value in tool_call.arguments|items %} + {{- '\n' }} + {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %} + {{- args_value }} + {{- '\n\n' }} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.role == "assistant" and message.reasoning_content is defined %} + {%- if message.reasoning_content -%} + {{ '\n' + message.reasoning_content.strip() + '' }} + {%- else -%} + {{ '\n' }} + {%- endif -%} + {%- if message.content.strip() -%} + {{ '\n' + message.content.strip() }} + {%- endif -%} + {%- else %} + {{- '\n' + message.content }} + {%- endif %} + {{- '<|im_end|>' + '\n' }} + {%- elif message.role == "tool" %} + {%- if loop.previtem and loop.previtem.role != "tool" %} + {{- '<|im_start|>user\n' }} + {%- endif %} + {{- '\n' }} + {{- message.content }} + {{- '\n\n' }} + {%- if not loop.last and loop.nextitem.role != "tool" %} + {{- '<|im_end|>\n' }} + {%- elif loop.last %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..73efa6fb2d1b181a592f20dbe459dccf094de8cc --- /dev/null +++ b/config.json @@ -0,0 +1,48 @@ +{ + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "auto_map": { + "AutoConfig": "configuration_glm4_moe.Glm4MoeConfig", + "AutoModel": "modeling_glm4_moe.Glm4MoeModel", + "AutoModelForCausalLM": "modeling_glm4_moe.Glm4MoeForCausalLM" + }, + "dtype": "bfloat16", + "eos_token_id": [ + 151334, + 151329 + ], + "first_k_dense_replace": 1, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 10944, + "max_position_embeddings": 131072, + "model_type": "glm4_moe", + "moe_intermediate_size": 1408, + "n_group": 1, + "n_routed_experts": 128, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 96, + "num_experts_per_tok": 8, + "num_hidden_layers": 46, + "num_key_value_heads": 8, + "num_nextn_predict_layers": 1, + "pad_token_id": 151329, + "partial_rotary_factor": 0.5, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "routed_scaling_factor": 1.0, + "tie_word_embeddings": false, + "topk_group": 1, + "transformers_version": "4.56.1", + "use_cache": false, + "use_grouped_mm": true, + "use_qk_norm": false, + "vocab_size": 151552 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d55c441b6d30971afacbc576e9cc07874730e5c1 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151334, + 151329 + ], + "pad_token_id": 151329, + "transformers_version": "4.56.1", + "use_cache": false +} diff --git a/model-00001-of-00048.safetensors b/model-00001-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2105862c5af820e6b2b502ebcd15a35275a78d71 --- /dev/null +++ b/model-00001-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:967b90d4be2368531443fb9adb8366c41bd8c725293d5d1b771b7abc33e8444b +size 4900192568 diff --git a/model-00002-of-00048.safetensors b/model-00002-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1627b30a119ea85fb345ed94821c96104aea9c7d --- /dev/null +++ b/model-00002-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:207ffd9658972bec70e358510cd809d1475509b730e21b3d213cfe9201fe5432 +size 4899977872 diff --git a/model-00003-of-00048.safetensors b/model-00003-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..85746bc0c76034ea559d858b776c0d1eb23b63ae --- /dev/null +++ b/model-00003-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b42cefa57b2af4918421e0a9948eaa361095828a5cc0cd0512d5c37a54f15fdc +size 4498785360 diff --git a/model-00004-of-00048.safetensors b/model-00004-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..61498cd5a7555af5f0a61bd113749a048f309a6e --- /dev/null +++ b/model-00004-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ca5291b97e429fd13d1eabf1a275fd10e8c8a0c477e32cfe1d93602ced8cd1 +size 4464885360 diff --git a/model-00005-of-00048.safetensors b/model-00005-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f8dcde5984d832be8e2bf22e02ee9f9cdd5bb1e8 --- /dev/null +++ b/model-00005-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f46ea18df396aec4917c3609568a6d8c77b26d17c7d86aa46322fb07d765ed19 +size 4464885360 diff --git a/model-00006-of-00048.safetensors b/model-00006-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e58cf6be546c5034ecd5b833796f4d6b14840631 --- /dev/null +++ b/model-00006-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac72dbc54e34505b9a67900411f8d8f735db38e0753d8c6793a544040c6936f6 +size 4464885360 diff --git a/model-00007-of-00048.safetensors b/model-00007-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a6d56a577097773ced508f2e9a6e546c0ad85054 --- /dev/null +++ b/model-00007-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52e89f060ba3dd4bc60fcf2e2fc72fd5dc20c880183ad2beb357b95dd86e2c53 +size 4464885360 diff --git a/model-00008-of-00048.safetensors b/model-00008-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b5ac1313131b46ff07014126482a88cc54a591c0 --- /dev/null +++ b/model-00008-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9609fdf9a158b4d0e42807a3e2a6191eef3890c0799a87def86b2cc1eb652925 +size 4464885360 diff --git a/model-00009-of-00048.safetensors b/model-00009-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e3f9227a0a1ae53f2f4d102829e122af44c3e7e6 --- /dev/null +++ b/model-00009-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:945d345943b9a9f83cd3620eccee5a1abdd3d140c859668ffdb27f1f2a9deea4 +size 4464885360 diff --git a/model-00010-of-00048.safetensors b/model-00010-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4bd504f8864afdaa2bf6f730b9ae3898247b4e9a --- /dev/null +++ b/model-00010-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cf5fe8a934476572d5a1c0e9f49ec94f62093b139e26f9604911fc948964806 +size 4464885360 diff --git a/model-00011-of-00048.safetensors b/model-00011-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d1f81460ef5daf10e0dca993204c2d50e96a6355 --- /dev/null +++ b/model-00011-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7050d5120945e22cbd1fad72a236866b58d4e9bfe71a35bc62ff8f7a48a04a +size 4464885360 diff --git a/model-00012-of-00048.safetensors b/model-00012-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..94d4647eed4e90f473f751c6fd5a20420e446a47 --- /dev/null +++ b/model-00012-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beebfb05c494db2beda081c60e92710c3b878ceef6daf8b3f07cba90ea9ea3ea +size 4464885496 diff --git a/model-00013-of-00048.safetensors b/model-00013-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..96f6b471ef055dd775f07a36c53939fb2f64480d --- /dev/null +++ b/model-00013-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cfd505ddf9a1e6b5d9ce64b73be6d211c46f316006887848b9f0f8de3742def +size 4464885752 diff --git a/model-00014-of-00048.safetensors b/model-00014-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..82a14c3845eb090bc1d0aeecf460eebed8abc958 --- /dev/null +++ b/model-00014-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5a8f4c75aa38211be6dfce55d2962b0297956d636bd7a895a35e0d4ee4e6de1 +size 4464885752 diff --git a/model-00015-of-00048.safetensors b/model-00015-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1c9aef6401876ef6b0faa68261ea46fa86e02fe7 --- /dev/null +++ b/model-00015-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2341508ad8d980555684ab079eaa3f1ae4876b2b56c736d87f3e4ec91b46e597 +size 4464885752 diff --git a/model-00016-of-00048.safetensors b/model-00016-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0d39b7597868744796086a4f1d45e3b50dd4da4a --- /dev/null +++ b/model-00016-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea5a9f64286fb5a721674da6be19dd22a99500e24a05c8ff0b12d9be02213ab +size 4464885752 diff --git a/model-00017-of-00048.safetensors b/model-00017-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..955b218de11a1804a3f429b8b4a1b0568415d287 --- /dev/null +++ b/model-00017-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45bcad8d7734173abc7dadae105a82558fe8709d366d9d3e55779c8ff85562e7 +size 4464885752 diff --git a/model-00018-of-00048.safetensors b/model-00018-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7f11283fc10b5395b1b770c3fe2f00ca8b1c3150 --- /dev/null +++ b/model-00018-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc1cf09608b51d266df825ccf74f93bec92b1fc3db684d9d6eeff8c81dd31341 +size 4464885752 diff --git a/model-00019-of-00048.safetensors b/model-00019-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..afb99ad61fe413f39394311ded52eb7e7d18751d --- /dev/null +++ b/model-00019-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc08c2864c2184941f3480073448db02eda18959f7b8270976f078f489e59d91 +size 4464885752 diff --git a/model-00020-of-00048.safetensors b/model-00020-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7b089b8ecc75ce306b53a87ec3d14cfe6b4fdd43 --- /dev/null +++ b/model-00020-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ffff3e4771e1cfaa129360b7c20ad0ee66f393d1cbf38d58509002ac02e4f7b +size 4464885752 diff --git a/model-00021-of-00048.safetensors b/model-00021-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4fdbe49b74f6518cb3dc70badf84399b3b2c6241 --- /dev/null +++ b/model-00021-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d34db1267502392d821a269970d472110a5cabc3a06f416fb30b0362c4e7ee64 +size 4464885752 diff --git a/model-00022-of-00048.safetensors b/model-00022-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..36b03cb99905fdfb8ad0da8312d1fabe2b276cda --- /dev/null +++ b/model-00022-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cfd9ca0f1e1bc78471572fdeb5062c9d5aecb954b64e4afc606c5226d58730f +size 4464885752 diff --git a/model-00023-of-00048.safetensors b/model-00023-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..77c4340ca5bd650cdf2be108f2f0339c9c5b3f27 --- /dev/null +++ b/model-00023-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d9bdf0743557667a293b68300c16b1c96118dbb958f575c975af4f5361bb2e8 +size 4464885752 diff --git a/model-00024-of-00048.safetensors b/model-00024-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0ca9fc5d0a0ab02e7d77f4a693a9970c9e762414 --- /dev/null +++ b/model-00024-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48e9d683696914f1de83464546eb67c5f48b02de75a650143af696de0d57aee6 +size 4464885752 diff --git a/model-00025-of-00048.safetensors b/model-00025-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..192a81898251bd5be129fdf590c9bf1dfa5912fd --- /dev/null +++ b/model-00025-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc960e31117861d4d921ad4f8346d845cbcf7d4ca5ecff02dbd078866969d7e0 +size 4464885752 diff --git a/model-00026-of-00048.safetensors b/model-00026-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d62bc9731f324587c4074465680ae451e9fe9097 --- /dev/null +++ b/model-00026-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fe9fd855efe8bc05a853779831dbc3386055812badee4e8f4b54f82da4cbf2d +size 4464885752 diff --git a/model-00027-of-00048.safetensors b/model-00027-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5e742e51a2a0a2c3d54fdec52d3728e66cb18852 --- /dev/null +++ b/model-00027-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd6ac423a7a2614fa271d58a07dccba7acdbd6dfad3b02a4a20d3be4417ecfac +size 4464885752 diff --git a/model-00028-of-00048.safetensors b/model-00028-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2767408da20e4897066ab133bdcbdea94dbf50c9 --- /dev/null +++ b/model-00028-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9d1973ec13ba62da83a89950041ddf66e4281ad42f2ef288e06b1e98acf0efa +size 4464885752 diff --git a/model-00029-of-00048.safetensors b/model-00029-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cc4f11d02e8496a310a1a0f93e782c406bdd0076 --- /dev/null +++ b/model-00029-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1093a9c656afa78bf0cbcfb076224d09935761fa876a7e4f08a4bf32e574340f +size 4464885752 diff --git a/model-00030-of-00048.safetensors b/model-00030-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..990c6083b3d60327e76062926765c5e1f17ea187 --- /dev/null +++ b/model-00030-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3e06e46d7485d17936b06f018a8ffba7c1de863572f4a6fff7c73d1ce6f4b7 +size 4464885752 diff --git a/model-00031-of-00048.safetensors b/model-00031-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..80f5c1a69f84b6cc9c5ec609ba08e3dcbb4b38a2 --- /dev/null +++ b/model-00031-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0c222c8e1c4bbd274f9a2bf76a9f515729f5dcb7d29b45d6081382bcc6ac00a +size 4464885752 diff --git a/model-00032-of-00048.safetensors b/model-00032-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..06f79b4200ea0e0d5f89b84a51cdff2ee06fab71 --- /dev/null +++ b/model-00032-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cca3840390f9ea224783b133f20720e790fec52ebe2c319c84505f4bfdc35b5 +size 4464885752 diff --git a/model-00033-of-00048.safetensors b/model-00033-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c1563004a52ae54db9140baadcc6c048806b91d --- /dev/null +++ b/model-00033-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da66e0a649c4727669c53e61f3a9a16363cb1d25ecfe18d881786c703ceb29ff +size 4464885752 diff --git a/model-00034-of-00048.safetensors b/model-00034-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f168126d5b5797cec06100316f1e024c14f2a272 --- /dev/null +++ b/model-00034-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:049ef2fffb7dd275cac9cd4408263d5950a4a0830b6c31160f556a511e0ac90b +size 4464885752 diff --git a/model-00035-of-00048.safetensors b/model-00035-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d4c61accd3a4a307a91737fbb87290c33fc402f8 --- /dev/null +++ b/model-00035-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a8e4fd694bb02b5d99595f679b40505bd1ad916349845bde834b592b6693a98 +size 4464885752 diff --git a/model-00036-of-00048.safetensors b/model-00036-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d10a403350ff680570f915522bcdf801fd344051 --- /dev/null +++ b/model-00036-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41cb430e60029d4e5e4b44d9a9902bd830c0d70a14485a57c0b0e8e20f3b3ad3 +size 4464885752 diff --git a/model-00037-of-00048.safetensors b/model-00037-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..767a98d71f98912d985bd865d0adecf029106651 --- /dev/null +++ b/model-00037-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bc707e48560d0d180fd92605b1684256a255ac8bc01dae71fbcbdd6fea71349 +size 4464885752 diff --git a/model-00038-of-00048.safetensors b/model-00038-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b1e17f5e1c6058619ed1d6ad0f6116543eb01d1c --- /dev/null +++ b/model-00038-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfd6a6e0394fe93187d246c3758b2377a882db5df3a686254466b0c179ef925a +size 4464885752 diff --git a/model-00039-of-00048.safetensors b/model-00039-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc86ff51aa71065a0a2a983050bd5d0db1486d39 --- /dev/null +++ b/model-00039-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d256836cdc23400f874a012fc669278a11161d1ec05253bb2255473d57d62b89 +size 4464885752 diff --git a/model-00040-of-00048.safetensors b/model-00040-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..39b13cb88be206f693c33d9e1082aa81cc83ef0b --- /dev/null +++ b/model-00040-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23581accb9dd228fffbdb4359fbba9c707babe47f65e588a8b38e2e565e6b4a6 +size 4464885752 diff --git a/model-00041-of-00048.safetensors b/model-00041-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..316840c1385ffa1d3e7152a0dbd16a56a10df06f --- /dev/null +++ b/model-00041-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9fcc2b5950f69b2a7446f67c72430fd1d154ebc1e0fbb18669213fb2f63456e +size 4464885752 diff --git a/model-00042-of-00048.safetensors b/model-00042-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..13956bf22446f05fe0b7e9c2731fbb68c2c895e6 --- /dev/null +++ b/model-00042-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d7543c9661050a50e102b8ed9076bea819167abbcb1f9c338fc32db3f0f33cf +size 4464885752 diff --git a/model-00043-of-00048.safetensors b/model-00043-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1726a4e5931e7b4dd54ad8623ce6efc8a2ef6119 --- /dev/null +++ b/model-00043-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4efc5f0e96ff05dbb6d8be6f77f0f0887f1c4535537c0cbbbf1811df40eb55c +size 4464885752 diff --git a/model-00044-of-00048.safetensors b/model-00044-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dae7224797c205bf352b32bc8dd992d0cd02586b --- /dev/null +++ b/model-00044-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f56a0dfea9262196dfac474f9bc611388e0e0fc44031eda05012f29c1abb51ad +size 4464885752 diff --git a/model-00045-of-00048.safetensors b/model-00045-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ea542d16ec6d0e9d762b8eee6dd14e0e974580c0 --- /dev/null +++ b/model-00045-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf52e38263d056aba4a712ab9698ca3e58bb3ecd583b333fad9f95aa84e1a7a +size 4464885752 diff --git a/model-00046-of-00048.safetensors b/model-00046-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..38bb9e3ddeea6dc20cf3992e5e34aba009324856 --- /dev/null +++ b/model-00046-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5161dba4a2b0c20c0cbab48a73e008935f571034342cb080dd09cc038043d075 +size 4464885752 diff --git a/model-00047-of-00048.safetensors b/model-00047-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f12b63d0b37acad430e37c6205981ce3f939661e --- /dev/null +++ b/model-00047-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d95a55b3cd7b9475e00893bf4427a89c762b7563bb868dcfe6d44673bd38a269 +size 4464885752 diff --git a/model-00048-of-00048.safetensors b/model-00048-of-00048.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..20f5c9c6ebd5b82257b24ef8e269803ec5b1191d --- /dev/null +++ b/model-00048-of-00048.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74c0a8979df7910996dfbdaf010138cc4cda1356948583ec7a880830690ac311 +size 2952821896 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..834d515870f7cc29f01a58ff380a0e8111f1b32b --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,17932 @@ +{ + "metadata": { + "total_size": 213704514048 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00048.safetensors", + "model.embed_tokens.weight": "model-00001-of-00048.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.100.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.100.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.100.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.101.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.101.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.101.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.102.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.102.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.102.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.103.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.103.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.103.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.104.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.104.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.104.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.105.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.105.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.105.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.106.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.106.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.106.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.107.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.107.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.107.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.108.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.108.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.108.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.109.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.109.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.109.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.110.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.110.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.110.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.111.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.111.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.111.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.112.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.112.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.112.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.113.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.113.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.113.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.114.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.114.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.114.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.115.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.115.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.115.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.116.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.116.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.116.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.117.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.117.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.117.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.118.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.118.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.118.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.119.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.119.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.119.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.120.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.120.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.120.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.121.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.121.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.121.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.122.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.122.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.122.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.123.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.123.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.123.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.124.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.124.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.124.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.125.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.125.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.125.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.126.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.126.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.126.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.127.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.127.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.127.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.64.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.64.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.64.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.65.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.65.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.65.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.66.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.66.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.66.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.67.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.67.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.67.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.68.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.68.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.68.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.69.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.69.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.69.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.70.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.70.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.70.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.71.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.71.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.71.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.72.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.72.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.72.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.73.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.73.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.73.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.74.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.74.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.74.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.75.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.75.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.75.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.76.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.76.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.76.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.77.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.77.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.77.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.78.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.78.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.78.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.79.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.79.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.79.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.80.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.80.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.80.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.81.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.81.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.81.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.82.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.82.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.82.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.83.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.83.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.83.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.84.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.84.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.84.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.85.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.85.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.85.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.86.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.86.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.86.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.87.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.87.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.87.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.88.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.88.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.88.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.89.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.89.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.89.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.90.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.90.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.90.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.91.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.91.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.91.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.92.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.92.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.92.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.93.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.93.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.93.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.94.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.94.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.94.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.95.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.95.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.95.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.96.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.96.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.96.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.97.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.97.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.97.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.98.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.98.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.98.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.99.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.experts.99.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.experts.99.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.1.mlp.gate.e_score_correction_bias": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.gate.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.100.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.100.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.101.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.101.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.102.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.102.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.103.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.103.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.104.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.104.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.105.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.105.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.106.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.106.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.107.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.107.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.108.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.108.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.109.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.109.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.110.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.110.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.111.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.111.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.112.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.112.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.113.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.113.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.114.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.114.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.115.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.115.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.116.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.116.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.117.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.117.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.118.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.118.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.119.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.119.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.120.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.120.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.121.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.121.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.122.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.122.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.123.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.123.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.124.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.124.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.125.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.125.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.126.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.126.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.127.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.127.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.64.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.64.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.65.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.65.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.66.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.66.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.67.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.67.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.68.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.68.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.69.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.69.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.70.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.70.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.71.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.71.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.72.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.72.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.73.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.73.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.74.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.74.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.75.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.75.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.76.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.76.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.77.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.77.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.78.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.78.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.79.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.79.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.80.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.80.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.81.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.81.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.82.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.82.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.83.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.83.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.84.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.84.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.85.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.85.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.86.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.86.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.87.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.87.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.88.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.88.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.89.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.89.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.90.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.90.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.91.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.91.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.92.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.92.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.93.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.93.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.94.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.94.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.95.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.95.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.96.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.96.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.97.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.97.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.98.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.98.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.99.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.experts.99.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.gate.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.11.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.100.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.100.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.101.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.101.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.102.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.102.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.103.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.103.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.104.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.104.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.105.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.105.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.106.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.106.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.107.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.107.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.108.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.108.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.109.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.109.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.110.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.110.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.111.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.111.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.112.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.112.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.113.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.113.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.114.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.114.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.115.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.115.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.116.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.116.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.117.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.117.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.118.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.118.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.119.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.119.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.120.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.120.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.121.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.121.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.122.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.122.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.123.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.123.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.124.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.124.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.125.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.125.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.126.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.126.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.127.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.127.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.64.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.64.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.65.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.65.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.66.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.66.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.67.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.67.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.68.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.68.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.69.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.69.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.70.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.70.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.71.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.71.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.72.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.72.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.73.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.73.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.74.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.74.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.75.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.75.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.76.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.76.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.77.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.77.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.78.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.78.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.79.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.79.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.80.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.80.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.81.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.81.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.82.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.82.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.83.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.83.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.84.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.84.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.85.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.85.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.86.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.86.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.87.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.87.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.88.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.88.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.89.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.89.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.90.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.90.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.91.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.91.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.92.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.92.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.93.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.93.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.94.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.94.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.95.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.95.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.96.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.96.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.97.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.97.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.98.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.98.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.99.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.experts.99.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.gate.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00013-of-00048.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.12.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.gate.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00014-of-00048.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.13.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.100.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.100.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.101.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.101.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.102.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.102.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.103.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.103.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.104.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.104.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.105.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.105.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.106.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.106.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.107.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.107.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.108.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.108.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.109.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.109.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.110.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.110.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.111.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.111.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.112.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.112.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.113.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.113.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.114.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.114.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.115.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.115.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.116.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.116.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.117.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.117.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.118.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.118.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.119.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.119.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.120.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.120.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.121.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.121.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.122.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.122.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.123.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.123.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.124.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.124.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.125.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.125.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.126.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.126.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.127.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.127.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.76.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.76.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.77.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.77.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.78.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.78.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.79.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.79.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.80.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.80.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.81.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.81.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.82.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.82.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.83.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.83.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.84.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.84.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.85.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.85.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.86.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.86.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.87.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.87.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.88.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.88.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.89.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.89.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.90.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.90.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.91.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.91.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.92.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.92.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.93.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.93.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.94.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.94.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.95.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.95.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.96.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.96.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.97.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.97.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.98.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.98.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.99.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.experts.99.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.gate.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00015-of-00048.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.100.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.100.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.101.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.101.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.102.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.102.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.103.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.103.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.104.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.104.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.105.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.105.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.106.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.106.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.107.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.107.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.108.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.108.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.109.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.109.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.110.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.110.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.111.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.111.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.112.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.112.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.113.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.113.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.114.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.114.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.115.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.115.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.116.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.116.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.117.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.117.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.118.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.118.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.119.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.119.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.120.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.120.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.121.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.121.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.122.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.122.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.123.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.123.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.124.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.124.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.125.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.125.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.126.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.126.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.127.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.127.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.64.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.64.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.65.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.65.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.66.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.66.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.67.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.67.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.68.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.68.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.69.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.69.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.70.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.70.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.71.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.71.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.72.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.72.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.73.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.73.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.74.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.74.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.75.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.75.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.76.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.76.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.77.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.77.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.78.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.78.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.79.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.79.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.80.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.80.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.81.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.81.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.82.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.82.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.83.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.83.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.84.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.84.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.85.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.85.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.86.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.86.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.87.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.87.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.88.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.88.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.89.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.89.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.90.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.90.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.91.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.91.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.92.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.92.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.93.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.93.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.94.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.94.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.95.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.95.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.96.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.96.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.97.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.97.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.98.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.98.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.99.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.experts.99.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.gate.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00016-of-00048.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.100.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.100.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.101.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.101.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.102.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.102.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.103.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.103.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.104.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.104.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.105.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.105.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.106.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.106.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.107.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.107.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.108.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.108.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.109.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.109.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.110.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.110.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.111.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.111.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.112.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.112.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.113.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.113.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.114.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.114.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.115.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.115.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.116.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.116.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.117.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.117.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.118.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.118.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.119.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.119.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.120.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.120.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.121.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.121.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.122.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.122.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.123.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.123.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.124.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.124.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.125.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.125.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.126.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.126.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.127.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.127.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.64.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.64.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.65.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.65.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.66.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.66.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.67.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.67.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.68.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.68.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.69.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.69.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.70.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.70.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.71.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.71.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.72.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.72.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.73.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.73.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.74.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.74.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.75.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.75.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.76.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.76.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.77.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.77.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.78.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.78.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.79.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.79.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.80.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.80.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.81.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.81.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.82.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.82.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.83.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.83.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.84.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.84.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.85.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.85.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.86.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.86.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.87.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.87.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.88.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.88.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.89.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.89.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.90.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.90.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.91.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.91.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.92.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.92.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.93.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.93.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.94.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.94.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.95.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.95.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.96.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.96.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.97.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.97.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.98.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.98.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.99.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.experts.99.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.gate.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00017-of-00048.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.100.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.100.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.101.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.101.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.102.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.102.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.103.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.103.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.104.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.104.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.105.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.105.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.106.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.106.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.107.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.107.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.108.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.108.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.109.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.109.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.110.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.110.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.111.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.111.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.112.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.112.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.113.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.113.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.114.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.114.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.115.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.115.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.116.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.116.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.117.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.117.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.118.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.118.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.119.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.119.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.120.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.120.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.121.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.121.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.122.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.122.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.123.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.123.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.124.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.124.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.125.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.125.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.126.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.126.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.127.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.127.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.64.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.64.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.65.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.65.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.66.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.66.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.67.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.67.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.68.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.68.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.69.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.69.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.70.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.70.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.71.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.71.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.72.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.72.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.73.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.73.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.74.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.74.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.75.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.75.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.76.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.76.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.77.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.77.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.78.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.78.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.79.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.79.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.80.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.80.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.81.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.81.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.82.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.82.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.83.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.83.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.84.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.84.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.85.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.85.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.86.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.86.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.87.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.87.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.88.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.88.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.89.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.89.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.90.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.90.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.91.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.91.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.92.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.92.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.93.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.93.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.94.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.94.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.95.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.95.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.96.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.96.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.97.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.97.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.98.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.98.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.99.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.experts.99.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.gate.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00018-of-00048.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.100.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.100.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.101.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.101.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.102.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.102.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.103.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.103.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.104.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.104.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.105.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.105.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.106.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.106.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.107.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.107.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.108.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.108.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.109.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.109.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.110.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.110.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.111.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.111.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.112.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.112.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.113.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.113.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.114.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.114.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.115.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.115.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.116.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.116.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.117.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.117.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.118.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.118.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.119.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.119.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.120.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.120.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.121.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.121.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.122.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.122.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.123.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.123.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.124.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.124.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.125.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.125.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.126.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.126.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.127.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.127.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.64.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.64.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.65.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.65.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.66.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.66.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.67.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.67.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.68.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.68.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.69.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.69.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.70.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.70.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.71.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.71.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.72.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.72.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.73.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.73.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.74.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.74.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.75.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.75.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.76.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.76.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.77.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.77.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.78.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.78.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.79.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.79.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.80.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.80.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.81.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.81.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.82.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.82.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.83.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.83.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.84.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.84.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.85.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.85.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.86.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.86.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.87.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.87.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.88.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.88.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.89.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.89.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.90.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.90.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.91.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.91.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.92.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.92.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.93.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.93.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.94.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.94.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.95.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.95.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.96.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.96.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.97.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.97.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.98.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.98.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.99.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.experts.99.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.gate.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00019-of-00048.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.100.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.100.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.101.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.101.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.102.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.102.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.103.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.103.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.104.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.104.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.105.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.105.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.106.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.106.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.107.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.107.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.108.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.108.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.109.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.109.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.110.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.110.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.111.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.111.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.112.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.112.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.113.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.113.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.114.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.114.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.115.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.115.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.116.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.116.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.117.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.117.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.118.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.118.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.119.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.119.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.120.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.120.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.121.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.121.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.122.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.122.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.123.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.123.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.124.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.124.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.125.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.125.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.126.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.126.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.127.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.127.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.64.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.64.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.65.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.65.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.66.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.66.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.67.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.67.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.68.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.68.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.69.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.69.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.70.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.70.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.71.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.71.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.72.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.72.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.73.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.73.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.74.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.74.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.75.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.75.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.76.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.76.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.77.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.77.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.78.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.78.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.79.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.79.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.80.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.80.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.81.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.81.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.82.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.82.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.83.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.83.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.84.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.84.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.85.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.85.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.86.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.86.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.87.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.87.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.88.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.88.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.89.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.89.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.90.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.90.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.91.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.91.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.92.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.92.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.93.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.93.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.94.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.94.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.95.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.95.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.96.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.96.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.97.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.97.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.98.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.98.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.99.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.experts.99.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.gate.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00020-of-00048.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.100.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.100.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.101.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.101.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.102.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.102.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.103.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.103.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.104.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.104.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.105.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.105.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.106.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.106.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.107.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.107.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.108.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.108.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.109.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.109.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.110.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.110.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.111.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.111.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.112.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.112.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.113.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.113.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.114.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.114.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.115.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.115.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.116.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.116.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.117.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.117.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.118.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.118.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.119.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.119.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.120.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.120.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.121.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.121.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.122.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.122.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.123.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.123.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.124.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.124.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.125.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.125.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.126.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.126.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.127.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.127.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.64.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.64.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.65.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.65.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.66.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.66.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.67.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.67.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.68.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.68.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.69.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.69.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.70.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.70.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.71.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.71.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.72.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.72.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.73.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.73.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.74.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.74.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.75.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.75.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.76.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.76.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.77.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.77.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.78.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.78.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.79.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.79.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.80.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.80.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.81.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.81.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.82.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.82.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.83.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.83.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.84.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.84.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.85.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.85.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.86.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.86.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.87.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.87.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.88.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.88.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.89.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.89.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.90.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.90.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.91.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.91.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.92.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.92.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.93.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.93.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.94.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.94.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.95.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.95.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.96.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.96.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.97.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.97.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.98.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.98.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.99.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.experts.99.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.gate.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00021-of-00048.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.100.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.100.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.100.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.101.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.101.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.101.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.102.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.102.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.102.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.103.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.103.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.103.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.104.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.104.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.104.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.105.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.105.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.105.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.106.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.106.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.106.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.107.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.107.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.107.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.108.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.108.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.108.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.109.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.109.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.109.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.110.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.110.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.110.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.111.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.111.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.111.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.112.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.112.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.112.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.113.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.113.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.113.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.114.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.114.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.114.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.115.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.115.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.115.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.116.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.116.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.116.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.117.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.117.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.117.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.118.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.118.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.118.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.119.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.119.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.119.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.120.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.120.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.120.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.121.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.121.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.121.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.122.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.122.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.122.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.123.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.123.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.123.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.124.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.124.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.124.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.125.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.125.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.125.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.126.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.126.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.126.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.127.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.127.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.127.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.64.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.64.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.64.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.65.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.65.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.65.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.66.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.66.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.66.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.67.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.67.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.67.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.68.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.68.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.68.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.69.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.69.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.69.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.70.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.70.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.70.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.71.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.71.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.71.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.72.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.72.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.72.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.73.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.73.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.73.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.74.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.74.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.74.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.75.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.75.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.75.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.76.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.76.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.76.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.77.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.77.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.77.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.78.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.78.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.78.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.79.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.79.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.79.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.80.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.80.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.80.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.81.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.81.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.81.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.82.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.82.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.82.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.83.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.83.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.83.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.84.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.84.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.84.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.85.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.85.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.85.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.86.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.86.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.86.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.87.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.87.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.87.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.88.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.88.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.88.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.89.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.89.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.89.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.90.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.90.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.90.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.91.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.91.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.91.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.92.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.92.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.92.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.93.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.93.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.93.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.94.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.94.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.94.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.95.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.95.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.95.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.96.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.96.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.96.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.97.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.97.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.97.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.98.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.98.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.98.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.99.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.experts.99.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.experts.99.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.2.mlp.gate.e_score_correction_bias": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.gate.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00004-of-00048.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.20.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.100.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.100.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.101.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.101.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.102.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.102.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.103.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.103.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.104.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.104.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.105.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.105.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.106.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.106.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.107.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.107.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.108.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.108.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.109.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.109.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.110.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.110.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.111.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.111.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.112.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.112.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.113.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.113.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.114.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.114.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.115.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.115.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.116.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.116.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.117.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.117.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.118.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.118.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.119.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.119.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.120.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.120.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.121.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.121.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.122.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.122.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.123.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.123.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.124.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.124.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.125.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.125.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.126.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.126.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.127.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.127.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.64.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.64.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.65.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.65.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.66.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.66.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.67.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.67.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.68.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.68.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.69.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.69.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.70.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.70.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.71.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.71.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.72.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.72.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.73.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.73.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.74.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.74.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.75.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.75.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.76.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.76.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.77.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.77.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.78.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.78.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.79.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.79.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.80.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.80.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.81.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.81.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.82.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.82.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.83.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.83.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.84.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.84.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.85.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.85.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.86.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.86.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.87.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.87.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.88.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.88.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.89.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.89.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.90.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.90.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.91.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.91.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.92.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.92.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.93.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.93.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.94.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.94.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.95.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.95.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.96.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.96.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.97.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.97.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.98.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.98.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.99.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.experts.99.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.gate.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00022-of-00048.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.21.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.100.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.100.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.101.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.101.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.102.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.102.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.103.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.103.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.104.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.104.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.105.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.105.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.106.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.106.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.107.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.107.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.108.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.108.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.109.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.109.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.110.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.110.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.111.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.111.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.112.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.112.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.113.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.113.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.114.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.114.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.115.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.115.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.116.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.116.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.117.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.117.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.118.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.118.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.119.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.119.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.120.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.120.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.121.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.121.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.122.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.122.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.123.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.123.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.124.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.124.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.125.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.125.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.126.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.126.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.127.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.127.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.64.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.64.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.65.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.65.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.66.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.66.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.67.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.67.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.68.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.68.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.69.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.69.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.70.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.70.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.71.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.71.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.72.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.72.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.73.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.73.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.74.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.74.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.75.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.75.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.76.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.76.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.77.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.77.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.78.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.78.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.79.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.79.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.80.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.80.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.81.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.81.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.82.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.82.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.83.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.83.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.84.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.84.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.85.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.85.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.86.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.86.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.87.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.87.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.88.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.88.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.89.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.89.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.90.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.90.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.91.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.91.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.92.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.92.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.93.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.93.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.94.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.94.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.95.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.95.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.96.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.96.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.97.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.97.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.98.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.98.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.99.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.experts.99.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.gate.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00023-of-00048.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.22.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.100.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.100.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.101.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.101.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.102.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.102.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.103.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.103.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.104.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.104.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.105.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.105.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.106.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.106.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.107.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.107.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.108.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.108.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.109.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.109.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.110.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.110.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.111.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.111.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.112.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.112.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.113.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.113.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.114.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.114.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.115.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.115.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.116.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.116.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.117.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.117.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.118.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.118.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.119.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.119.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.120.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.120.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.121.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.121.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.122.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.122.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.123.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.123.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.124.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.124.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.125.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.125.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.126.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.126.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.127.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.127.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.64.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.64.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.65.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.65.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.66.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.66.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.67.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.67.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.68.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.68.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.69.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.69.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.70.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.70.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.71.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.71.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.72.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.72.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.73.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.73.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.74.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.74.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.75.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.75.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.76.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.76.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.77.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.77.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.78.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.78.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.79.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.79.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.80.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.80.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.81.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.81.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.82.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.82.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.83.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.83.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.84.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.84.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.85.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.85.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.86.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.86.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.87.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.87.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.88.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.88.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.89.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.89.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.90.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.90.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.91.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.91.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.92.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.92.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.93.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.93.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.94.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.94.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.95.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.95.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.96.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.96.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.97.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.97.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.98.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.98.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.99.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.experts.99.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.gate.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00024-of-00048.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.100.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.100.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.101.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.101.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.102.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.102.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.103.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.103.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.104.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.104.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.105.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.105.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.106.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.106.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.107.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.107.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.108.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.108.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.109.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.109.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.110.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.110.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.111.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.111.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.112.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.112.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.113.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.113.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.114.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.114.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.115.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.115.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.116.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.116.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.117.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.117.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.118.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.118.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.119.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.119.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.120.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.120.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.121.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.121.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.122.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.122.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.123.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.123.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.124.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.124.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.125.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.125.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.126.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.126.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.127.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.127.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.64.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.64.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.65.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.65.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.66.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.66.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.67.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.67.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.68.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.68.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.69.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.69.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.70.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.70.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.71.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.71.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.72.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.72.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.73.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.73.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.74.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.74.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.75.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.75.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.76.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.76.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.77.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.77.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.78.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.78.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.79.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.79.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.80.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.80.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.81.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.81.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.82.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.82.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.83.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.83.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.84.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.84.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.85.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.85.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.86.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.86.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.87.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.87.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.88.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.88.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.89.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.89.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.90.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.90.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.91.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.91.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.92.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.92.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.93.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.93.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.94.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.94.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.95.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.95.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.96.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.96.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.97.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.97.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.98.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.98.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.99.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.experts.99.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.gate.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00025-of-00048.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.24.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.100.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.100.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.101.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.101.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.102.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.102.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.103.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.103.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.104.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.104.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.105.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.105.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.106.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.106.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.107.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.107.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.108.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.108.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.109.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.109.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.110.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.110.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.111.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.111.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.112.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.112.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.113.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.113.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.114.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.114.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.115.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.115.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.116.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.116.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.117.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.117.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.118.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.118.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.119.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.119.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.120.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.120.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.121.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.121.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.122.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.122.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.123.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.123.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.124.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.124.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.125.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.125.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.126.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.126.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.127.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.127.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.64.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.64.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.65.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.65.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.66.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.66.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.67.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.67.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.68.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.68.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.69.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.69.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.70.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.70.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.71.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.71.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.72.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.72.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.73.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.73.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.74.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.74.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.75.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.75.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.76.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.76.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.77.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.77.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.78.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.78.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.79.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.79.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.80.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.80.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.81.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.81.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.82.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.82.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.83.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.83.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.84.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.84.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.85.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.85.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.86.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.86.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.87.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.87.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.88.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.88.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.89.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.89.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.90.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.90.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.91.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.91.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.92.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.92.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.93.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.93.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.94.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.94.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.95.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.95.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.96.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.96.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.97.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.97.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.98.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.98.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.99.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.experts.99.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.gate.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00026-of-00048.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.100.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.100.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.101.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.101.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.102.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.102.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.103.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.103.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.104.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.104.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.105.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.105.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.106.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.106.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.107.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.107.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.108.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.108.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.109.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.109.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.110.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.110.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.111.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.111.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.112.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.112.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.113.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.113.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.114.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.114.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.115.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.115.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.116.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.116.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.117.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.117.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.118.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.118.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.119.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.119.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.120.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.120.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.121.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.121.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.122.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.122.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.123.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.123.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.124.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.124.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.125.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.125.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.126.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.126.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.127.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.127.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.64.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.64.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.65.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.65.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.66.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.66.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.67.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.67.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.68.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.68.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.69.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.69.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.70.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.70.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.71.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.71.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.72.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.72.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.73.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.73.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.74.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.74.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.75.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.75.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.76.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.76.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.77.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.77.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.78.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.78.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.79.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.79.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.80.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.80.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.81.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.81.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.82.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.82.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.83.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.83.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.84.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.84.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.85.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.85.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.86.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.86.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.87.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.87.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.88.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.88.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.89.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.89.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.90.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.90.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.91.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.91.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.92.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.92.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.93.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.93.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.94.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.94.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.95.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.95.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.96.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.96.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.97.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.97.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.98.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.98.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.99.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.experts.99.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.gate.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00027-of-00048.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.26.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.64.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.64.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.65.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.65.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.66.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.66.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.67.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.67.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.68.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.68.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.69.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.69.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.70.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.70.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.71.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.71.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.72.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.72.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.73.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.73.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.74.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.74.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.75.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.75.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.76.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.76.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.77.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.77.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.78.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.78.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.79.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.79.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.80.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.80.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.81.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.81.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.82.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.82.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.83.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.83.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.84.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.84.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.85.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.85.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.86.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.86.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.87.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.87.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.88.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.88.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.89.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.89.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.90.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.90.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.gate.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00028-of-00048.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.27.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.gate.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00029-of-00048.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.28.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.gate.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00030-of-00048.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.29.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.100.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.100.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.101.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.101.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.102.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.102.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.103.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.103.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.104.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.104.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.105.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.105.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.106.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.106.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.107.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.107.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.108.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.108.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.109.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.109.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.110.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.110.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.111.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.111.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.112.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.112.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.113.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.113.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.114.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.114.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.115.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.115.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.116.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.116.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.117.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.117.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.118.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.118.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.119.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.119.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.120.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.120.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.121.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.121.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.122.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.122.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.123.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.123.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.124.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.124.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.125.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.125.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.126.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.126.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.127.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.127.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.64.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.64.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.65.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.65.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.66.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.66.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.67.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.67.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.68.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.68.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.69.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.69.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.70.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.70.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.71.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.71.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.72.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.72.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.73.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.73.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.74.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.74.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.75.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.75.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.76.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.76.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.77.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.77.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.78.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.78.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.79.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.79.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.80.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.80.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.81.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.81.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.82.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.82.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.83.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.83.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.84.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.84.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.85.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.85.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.86.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.86.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.87.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.87.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.88.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.88.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.89.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.89.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.90.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.90.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.91.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.91.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.92.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.92.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.93.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.93.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.94.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.94.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.95.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.95.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.96.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.96.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.97.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.97.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.98.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.98.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.99.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.experts.99.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.gate.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00031-of-00048.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.100.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.100.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.101.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.101.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.102.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.102.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.103.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.103.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.104.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.104.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.105.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.105.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.106.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.106.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.107.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.107.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.108.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.108.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.109.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.109.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.110.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.110.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.111.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.111.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.112.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.112.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.113.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.113.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.114.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.114.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.115.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.115.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.116.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.116.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.117.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.117.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.118.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.118.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.119.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.119.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.120.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.120.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.121.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.121.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.122.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.122.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.123.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.123.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.124.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.124.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.125.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.125.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.126.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.126.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.127.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.127.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.64.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.64.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.65.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.65.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.66.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.66.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.67.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.67.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.68.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.68.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.69.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.69.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.70.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.70.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.71.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.71.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.72.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.72.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.73.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.73.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.74.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.74.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.75.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.75.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.76.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.76.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.77.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.77.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.78.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.78.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.79.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.79.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.80.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.80.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.81.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.81.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.82.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.82.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.83.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.83.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.84.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.84.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.85.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.85.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.86.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.86.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.87.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.87.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.88.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.88.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.89.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.89.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.90.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.90.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.91.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.91.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.92.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.92.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.93.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.93.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.94.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.94.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.95.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.95.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.96.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.96.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.97.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.97.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.98.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.98.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.99.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.experts.99.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.gate.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00005-of-00048.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.100.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.100.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.101.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.101.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.102.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.102.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.103.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.103.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.104.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.104.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.105.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.105.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.106.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.106.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.107.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.107.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.108.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.108.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.109.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.109.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.110.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.110.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.111.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.111.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.112.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.112.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.113.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.113.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.114.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.114.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.115.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.115.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.116.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.116.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.117.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.117.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.118.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.118.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.119.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.119.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.120.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.120.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.121.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.121.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.122.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.122.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.123.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.123.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.124.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.124.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.125.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.125.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.126.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.126.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.127.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.127.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.64.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.64.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.65.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.65.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.66.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.66.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.67.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.67.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.68.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.68.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.69.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.69.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.70.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.70.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.71.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.71.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.72.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.72.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.73.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.73.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.74.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.74.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.75.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.75.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.76.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.76.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.77.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.77.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.78.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.78.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.79.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.79.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.80.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.80.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.81.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.81.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.82.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.82.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.83.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.83.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.84.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.84.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.85.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.85.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.86.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.86.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.87.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.87.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.88.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.88.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.89.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.89.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.90.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.90.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.91.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.91.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.92.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.92.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.93.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.93.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.94.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.94.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.95.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.95.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.96.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.96.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.97.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.97.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.98.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.98.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.99.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.experts.99.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.gate.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00032-of-00048.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.31.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.100.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.100.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.101.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.101.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.102.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.102.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.103.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.103.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.104.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.104.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.105.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.105.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.106.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.106.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.107.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.107.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.108.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.108.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.109.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.109.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.110.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.110.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.111.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.111.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.112.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.112.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.113.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.113.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.114.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.114.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.115.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.115.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.116.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.116.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.117.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.117.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.118.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.118.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.119.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.119.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.120.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.120.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.121.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.121.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.122.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.122.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.123.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.123.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.124.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.124.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.125.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.125.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.126.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.126.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.127.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.127.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.64.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.64.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.65.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.65.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.66.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.66.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.67.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.67.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.68.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.68.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.69.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.69.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.70.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.70.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.71.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.71.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.72.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.72.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.73.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.73.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.74.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.74.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.75.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.75.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.76.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.76.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.77.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.77.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.78.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.78.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.79.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.79.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.80.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.80.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.81.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.81.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.82.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.82.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.83.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.83.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.84.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.84.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.85.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.85.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.86.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.86.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.87.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.87.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.88.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.88.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.89.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.89.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.90.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.90.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.91.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.91.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.92.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.92.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.93.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.93.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.94.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.94.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.95.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.95.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.96.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.96.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.97.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.97.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.98.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.98.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.99.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.experts.99.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.gate.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00033-of-00048.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.32.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.100.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.100.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.100.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.101.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.101.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.101.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.102.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.102.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.102.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.103.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.103.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.103.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.104.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.104.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.104.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.105.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.105.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.105.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.106.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.106.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.106.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.107.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.107.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.107.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.108.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.108.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.108.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.109.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.109.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.109.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.110.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.110.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.110.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.111.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.111.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.111.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.112.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.112.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.112.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.113.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.113.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.113.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.114.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.114.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.114.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.115.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.115.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.115.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.116.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.116.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.116.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.117.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.117.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.117.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.118.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.118.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.118.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.119.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.119.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.119.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.120.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.120.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.120.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.121.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.121.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.121.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.122.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.122.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.122.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.123.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.123.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.123.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.124.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.124.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.124.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.125.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.125.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.125.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.126.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.126.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.126.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.127.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.127.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.127.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.64.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.64.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.64.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.65.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.65.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.65.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.66.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.66.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.66.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.67.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.67.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.67.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.68.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.68.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.68.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.69.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.69.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.69.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.70.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.70.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.70.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.71.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.71.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.71.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.72.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.72.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.72.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.73.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.73.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.73.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.74.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.74.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.74.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.75.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.75.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.75.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.76.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.76.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.76.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.77.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.77.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.77.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.78.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.78.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.78.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.79.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.79.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.79.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.80.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.80.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.80.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.81.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.81.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.81.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.82.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.82.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.82.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.83.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.83.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.83.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.84.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.84.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.84.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.85.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.85.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.85.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.86.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.86.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.86.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.87.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.87.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.87.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.88.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.88.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.88.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.89.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.89.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.89.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.90.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.90.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.90.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.91.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.91.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.91.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.92.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.92.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.92.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.93.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.93.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.93.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.94.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.94.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.94.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.95.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.95.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.95.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.96.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.96.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.96.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.97.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.97.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.97.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.98.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.98.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.98.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.99.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.experts.99.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.experts.99.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.gate.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00034-of-00048.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.33.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.100.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.100.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.100.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.101.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.101.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.101.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.102.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.102.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.102.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.103.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.103.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.103.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.104.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.104.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.104.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.105.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.105.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.105.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.106.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.106.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.106.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.107.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.107.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.107.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.108.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.108.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.108.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.109.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.109.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.109.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.110.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.110.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.110.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.111.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.111.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.111.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.112.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.112.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.112.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.113.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.113.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.113.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.114.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.114.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.114.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.115.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.115.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.115.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.116.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.116.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.116.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.117.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.117.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.117.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.118.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.118.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.118.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.119.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.119.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.119.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.120.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.120.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.120.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.121.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.121.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.121.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.122.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.122.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.122.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.123.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.123.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.123.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.124.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.124.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.124.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.125.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.125.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.125.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.126.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.126.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.126.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.127.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.127.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.127.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.64.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.64.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.64.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.65.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.65.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.65.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.66.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.66.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.66.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.67.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.67.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.67.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.68.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.68.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.68.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.69.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.69.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.69.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.70.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.70.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.70.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.71.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.71.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.71.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.72.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.72.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.72.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.73.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.73.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.73.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.74.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.74.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.74.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.75.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.75.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.75.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.76.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.76.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.76.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.77.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.77.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.77.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.78.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.78.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.78.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.79.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.79.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.79.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.80.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.80.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.80.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.81.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.81.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.81.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.82.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.82.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.82.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.83.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.83.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.83.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.84.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.84.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.84.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.85.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.85.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.85.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.86.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.86.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.86.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.87.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.87.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.87.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.88.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.88.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.88.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.89.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.89.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.89.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.90.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.90.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.90.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.91.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.91.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.91.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.92.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.92.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.92.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.93.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.93.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.93.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.94.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.94.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.94.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.95.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.95.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.95.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.96.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.96.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.96.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.97.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.97.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.97.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.98.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.98.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.98.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.99.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.experts.99.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.experts.99.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.gate.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00035-of-00048.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.34.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.100.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.100.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.100.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.101.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.101.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.101.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.102.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.102.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.102.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.103.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.103.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.103.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.104.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.104.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.104.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.105.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.105.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.105.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.106.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.106.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.106.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.107.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.107.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.107.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.108.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.108.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.108.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.109.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.109.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.109.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.110.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.110.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.110.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.111.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.111.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.111.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.112.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.112.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.112.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.113.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.113.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.113.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.114.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.114.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.114.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.115.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.115.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.115.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.116.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.116.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.116.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.117.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.117.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.117.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.118.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.118.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.118.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.119.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.119.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.119.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.120.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.120.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.120.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.121.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.121.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.121.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.122.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.122.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.122.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.123.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.123.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.123.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.124.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.124.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.124.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.125.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.125.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.125.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.126.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.126.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.126.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.127.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.127.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.127.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.64.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.64.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.64.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.65.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.65.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.65.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.66.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.66.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.66.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.67.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.67.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.67.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.68.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.68.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.68.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.69.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.69.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.69.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.70.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.70.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.70.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.71.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.71.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.71.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.72.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.72.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.72.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.73.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.73.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.73.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.74.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.74.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.74.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.75.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.75.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.75.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.76.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.76.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.76.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.77.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.77.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.77.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.78.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.78.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.78.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.79.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.79.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.79.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.80.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.80.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.80.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.81.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.81.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.81.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.82.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.82.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.82.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.83.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.83.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.83.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.84.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.84.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.84.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.85.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.85.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.85.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.86.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.86.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.86.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.87.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.87.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.87.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.88.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.88.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.88.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.89.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.89.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.89.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.90.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.90.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.90.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.91.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.91.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.91.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.92.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.92.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.92.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.93.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.93.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.93.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.94.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.94.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.94.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.95.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.95.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.95.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.96.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.96.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.96.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.97.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.97.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.97.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.98.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.98.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.98.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.99.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.experts.99.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.experts.99.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.gate.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00036-of-00048.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.35.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.100.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.100.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.100.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.101.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.101.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.101.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.102.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.102.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.102.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.103.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.103.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.103.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.104.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.104.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.104.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.105.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.105.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.105.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.106.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.106.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.106.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.107.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.107.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.107.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.108.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.108.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.108.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.109.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.109.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.109.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.110.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.110.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.110.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.111.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.111.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.111.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.112.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.112.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.112.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.113.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.113.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.113.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.114.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.114.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.114.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.115.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.115.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.115.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.116.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.116.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.116.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.117.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.117.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.117.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.118.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.118.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.118.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.119.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.119.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.119.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.120.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.120.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.120.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.121.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.121.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.121.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.122.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.122.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.122.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.123.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.123.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.123.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.124.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.124.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.124.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.125.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.125.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.125.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.126.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.126.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.126.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.127.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.127.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.127.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.64.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.64.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.64.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.65.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.65.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.65.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.66.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.66.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.66.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.67.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.67.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.67.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.68.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.68.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.68.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.69.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.69.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.69.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.70.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.70.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.70.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.71.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.71.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.71.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.72.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.72.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.72.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.73.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.73.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.73.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.74.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.74.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.74.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.75.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.75.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.75.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.76.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.76.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.76.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.77.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.77.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.77.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.78.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.78.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.78.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.79.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.79.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.79.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.80.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.80.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.80.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.81.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.81.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.81.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.82.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.82.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.82.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.83.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.83.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.83.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.84.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.84.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.84.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.85.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.85.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.85.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.86.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.86.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.86.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.87.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.87.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.87.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.88.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.88.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.88.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.89.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.89.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.89.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.90.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.90.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.90.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.91.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.91.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.91.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.92.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.92.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.92.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.93.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.93.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.93.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.94.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.94.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.94.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.95.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.95.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.95.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.96.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.96.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.96.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.97.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.97.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.97.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.98.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.98.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.98.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.99.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.experts.99.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.experts.99.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.gate.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00037-of-00048.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.36.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.100.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.100.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.100.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.101.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.101.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.101.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.102.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.102.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.102.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.103.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.103.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.103.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.104.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.104.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.104.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.105.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.105.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.105.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.106.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.106.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.106.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.107.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.107.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.107.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.108.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.108.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.108.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.109.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.109.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.109.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.110.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.110.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.110.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.111.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.111.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.111.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.112.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.112.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.112.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.113.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.113.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.113.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.114.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.114.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.114.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.115.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.115.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.115.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.116.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.116.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.116.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.117.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.117.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.117.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.118.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.118.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.118.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.119.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.119.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.119.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.120.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.120.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.120.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.121.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.121.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.121.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.122.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.122.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.122.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.123.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.123.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.123.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.124.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.124.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.124.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.125.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.125.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.125.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.126.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.126.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.126.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.127.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.127.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.127.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.64.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.64.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.64.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.65.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.65.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.65.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.66.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.66.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.66.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.67.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.67.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.67.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.68.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.68.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.68.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.69.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.69.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.69.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.70.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.70.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.70.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.71.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.71.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.71.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.72.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.72.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.72.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.73.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.73.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.73.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.74.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.74.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.74.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.75.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.75.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.75.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.76.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.76.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.76.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.77.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.77.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.77.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.78.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.78.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.78.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.79.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.79.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.79.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.80.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.80.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.80.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.81.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.81.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.81.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.82.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.82.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.82.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.83.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.83.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.83.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.84.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.84.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.84.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.85.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.85.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.85.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.86.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.86.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.86.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.87.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.87.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.87.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.88.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.88.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.88.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.89.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.89.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.89.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.90.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.90.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.90.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.91.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.91.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.91.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.92.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.92.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.92.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.93.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.93.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.93.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.94.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.94.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.94.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.95.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.95.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.95.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.96.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.96.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.96.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.97.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.97.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.97.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.98.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.98.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.98.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.99.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.experts.99.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.experts.99.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.gate.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00038-of-00048.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.37.input_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.100.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.100.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.100.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.101.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.101.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.101.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.102.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.102.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.102.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.103.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.103.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.103.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.104.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.104.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.104.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.105.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.105.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.105.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.106.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.106.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.106.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.107.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.107.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.107.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.108.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.108.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.108.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.109.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.109.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.109.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.110.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.110.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.110.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.111.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.111.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.111.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.112.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.112.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.112.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.113.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.113.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.113.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.114.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.114.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.114.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.115.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.115.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.115.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.116.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.116.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.116.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.117.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.117.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.117.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.118.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.118.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.118.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.119.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.119.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.119.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.120.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.120.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.120.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.121.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.121.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.121.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.122.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.122.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.122.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.123.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.123.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.123.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.124.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.124.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.124.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.125.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.125.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.125.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.126.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.126.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.126.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.127.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.127.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.127.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.64.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.64.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.64.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.65.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.65.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.65.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.66.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.66.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.66.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.67.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.67.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.67.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.68.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.68.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.68.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.69.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.69.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.69.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.70.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.70.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.70.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.71.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.71.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.71.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.72.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.72.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.72.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.73.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.73.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.73.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.74.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.74.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.74.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.75.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.75.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.75.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.76.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.76.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.76.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.77.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.77.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.77.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.78.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.78.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.78.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.79.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.79.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.79.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.80.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.80.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.80.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.81.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.81.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.81.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.82.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.82.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.82.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.83.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.83.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.83.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.84.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.84.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.84.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.85.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.85.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.85.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.86.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.86.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.86.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.87.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.87.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.87.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.88.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.88.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.88.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.89.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.89.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.89.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.90.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.90.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.90.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.91.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.91.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.91.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.92.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.92.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.92.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.93.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.93.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.93.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.94.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.94.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.94.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.95.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.95.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.95.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.96.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.96.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.96.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.97.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.97.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.97.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.98.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.98.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.98.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.99.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.experts.99.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.experts.99.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.gate.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00039-of-00048.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00002-of-00048.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00048.safetensors", + "model.layers.38.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.100.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.100.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.100.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.101.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.101.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.101.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.102.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.102.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.102.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.103.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.103.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.103.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.104.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.104.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.104.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.105.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.105.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.105.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.106.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.106.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.106.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.107.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.107.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.107.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.108.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.108.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.108.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.109.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.109.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.109.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.110.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.110.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.110.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.111.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.111.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.111.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.112.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.112.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.112.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.113.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.113.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.113.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.114.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.114.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.114.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.115.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.115.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.115.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.116.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.116.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.116.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.117.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.117.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.117.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.118.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.118.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.118.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.119.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.119.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.119.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.120.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.120.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.120.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.121.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.121.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.121.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.122.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.122.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.122.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.123.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.123.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.123.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.124.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.124.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.124.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.125.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.125.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.125.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.126.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.126.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.126.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.127.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.127.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.127.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.64.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.64.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.64.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.65.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.65.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.65.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.66.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.66.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.66.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.67.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.67.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.67.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.68.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.68.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.68.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.69.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.69.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.69.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.70.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.70.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.70.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.71.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.71.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.71.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.72.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.72.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.72.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.73.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.73.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.73.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.74.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.74.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.74.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.75.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.75.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.75.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.76.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.76.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.76.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.77.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.77.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.77.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.78.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.78.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.78.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.79.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.79.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.79.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.80.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.80.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.80.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.81.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.81.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.81.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.82.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.82.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.82.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.83.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.83.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.83.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.84.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.84.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.84.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.85.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.85.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.85.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.86.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.86.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.86.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.87.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.87.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.87.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.88.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.88.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.88.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.89.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.89.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.89.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.90.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.90.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.90.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.91.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.91.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.91.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.92.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.92.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.92.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.93.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.93.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.93.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.94.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.94.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.94.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.95.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.95.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.95.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.96.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.96.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.96.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.97.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.97.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.97.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.98.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.98.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.98.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.99.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.experts.99.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.experts.99.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.gate.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00040-of-00048.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.39.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.100.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.100.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.100.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.101.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.101.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.101.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.102.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.102.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.102.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.103.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.103.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.103.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.104.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.104.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.104.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.105.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.105.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.105.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.106.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.106.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.106.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.107.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.107.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.107.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.108.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.108.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.108.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.109.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.109.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.109.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.110.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.110.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.110.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.111.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.111.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.111.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.112.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.112.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.112.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.113.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.113.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.113.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.114.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.114.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.114.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.115.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.115.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.115.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.116.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.116.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.116.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.117.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.117.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.117.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.118.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.118.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.118.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.119.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.119.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.119.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.120.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.120.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.120.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.121.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.121.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.121.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.122.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.122.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.122.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.123.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.123.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.123.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.124.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.124.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.124.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.125.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.125.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.125.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.126.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.126.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.126.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.127.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.127.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.127.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.64.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.64.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.64.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.65.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.65.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.65.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.66.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.66.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.66.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.67.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.67.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.67.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.68.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.68.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.68.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.69.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.69.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.69.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.70.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.70.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.70.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.71.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.71.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.71.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.72.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.72.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.72.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.73.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.73.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.73.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.74.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.74.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.74.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.75.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.75.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.75.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.76.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.76.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.76.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.77.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.77.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.77.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.78.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.78.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.78.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.79.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.79.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.79.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.80.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.80.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.80.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.81.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.81.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.81.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.82.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.82.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.82.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.83.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.83.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.83.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.84.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.84.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.84.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.85.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.85.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.85.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.86.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.86.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.86.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.87.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.87.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.87.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.88.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.88.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.88.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.89.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.89.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.89.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.90.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.90.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.90.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.91.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.91.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.91.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.92.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.92.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.92.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.93.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.93.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.93.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.94.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.94.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.94.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.95.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.95.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.95.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.96.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.96.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.96.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.97.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.97.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.97.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.98.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.98.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.98.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.99.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.experts.99.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.experts.99.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.gate.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00041-of-00048.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.100.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.100.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.101.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.101.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.102.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.102.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.103.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.103.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.104.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.104.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.105.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.105.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.106.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.106.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.107.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.107.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.108.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.108.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.109.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.109.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.110.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.110.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.111.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.111.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.112.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.112.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.113.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.113.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.114.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.114.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.115.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.115.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.116.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.116.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.117.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.117.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.118.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.118.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.119.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.119.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.120.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.120.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.121.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.121.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.122.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.122.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.123.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.123.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.124.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.124.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.125.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.125.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.126.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.126.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.127.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.127.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.64.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.64.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.65.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.65.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.66.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.66.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.67.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.67.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.68.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.68.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.69.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.69.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.70.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.70.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.71.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.71.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.72.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.72.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.73.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.73.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.74.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.74.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.75.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.75.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.76.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.76.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.77.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.77.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.78.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.78.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.79.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.79.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.80.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.80.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.81.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.81.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.82.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.82.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.83.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.83.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.84.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.84.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.85.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.85.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.86.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.86.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.87.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.87.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.88.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.88.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.89.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.89.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.90.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.90.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.91.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.91.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.92.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.92.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.93.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.93.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.94.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.94.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.95.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.95.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.96.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.96.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.97.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.97.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.98.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.98.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.99.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.experts.99.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.gate.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00006-of-00048.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.40.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.100.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.100.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.100.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.101.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.101.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.101.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.102.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.102.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.102.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.103.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.103.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.103.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.104.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.104.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.104.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.105.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.105.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.105.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.106.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.106.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.106.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.107.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.107.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.107.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.108.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.108.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.108.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.109.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.109.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.109.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.110.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.110.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.110.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.111.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.111.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.111.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.112.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.112.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.112.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.113.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.113.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.113.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.114.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.114.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.114.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.115.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.115.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.115.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.116.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.116.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.116.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.117.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.117.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.117.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.118.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.118.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.118.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.119.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.119.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.119.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.120.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.120.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.120.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.121.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.121.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.121.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.122.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.122.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.122.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.123.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.123.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.123.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.124.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.124.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.124.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.125.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.125.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.125.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.126.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.126.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.126.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.127.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.127.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.127.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.64.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.64.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.64.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.65.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.65.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.65.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.66.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.66.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.66.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.67.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.67.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.67.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.68.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.68.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.68.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.69.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.69.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.69.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.70.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.70.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.70.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.71.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.71.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.71.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.72.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.72.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.72.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.73.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.73.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.73.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.74.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.74.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.74.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.75.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.75.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.75.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.76.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.76.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.76.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.77.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.77.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.77.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.78.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.78.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.78.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.79.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.79.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.79.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.80.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.80.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.80.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.81.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.81.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.81.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.82.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.82.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.82.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.83.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.83.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.83.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.84.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.84.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.84.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.85.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.85.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.85.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.86.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.86.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.86.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.87.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.87.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.87.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.88.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.88.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.88.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.89.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.89.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.89.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.90.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.90.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.90.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.91.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.91.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.91.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.92.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.92.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.92.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.93.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.93.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.93.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.94.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.94.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.94.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.95.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.95.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.95.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.96.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.96.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.96.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.97.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.97.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.97.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.98.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.98.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.98.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.99.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.experts.99.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.experts.99.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.gate.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00042-of-00048.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.41.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.100.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.100.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.100.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.101.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.101.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.101.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.102.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.102.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.102.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.103.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.103.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.103.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.104.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.104.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.104.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.105.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.105.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.105.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.106.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.106.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.106.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.107.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.107.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.107.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.108.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.108.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.108.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.109.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.109.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.109.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.110.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.110.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.110.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.111.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.111.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.111.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.112.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.112.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.112.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.113.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.113.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.113.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.114.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.114.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.114.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.115.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.115.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.115.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.116.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.116.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.116.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.117.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.117.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.117.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.118.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.118.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.118.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.119.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.119.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.119.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.120.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.120.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.120.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.121.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.121.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.121.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.122.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.122.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.122.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.123.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.123.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.123.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.124.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.124.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.124.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.125.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.125.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.125.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.126.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.126.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.126.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.127.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.127.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.127.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.64.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.64.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.64.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.65.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.65.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.65.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.66.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.66.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.66.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.67.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.67.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.67.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.68.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.68.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.68.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.69.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.69.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.69.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.70.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.70.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.70.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.71.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.71.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.71.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.72.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.72.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.72.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.73.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.73.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.73.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.74.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.74.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.74.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.75.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.75.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.75.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.76.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.76.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.76.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.77.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.77.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.77.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.78.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.78.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.78.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.79.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.79.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.79.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.80.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.80.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.80.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.81.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.81.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.81.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.82.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.82.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.82.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.83.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.83.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.83.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.84.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.84.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.84.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.85.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.85.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.85.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.86.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.86.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.86.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.87.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.87.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.87.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.88.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.88.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.88.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.89.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.89.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.89.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.90.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.90.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.90.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.91.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.91.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.91.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.92.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.92.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.92.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.93.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.93.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.93.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.94.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.94.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.94.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.95.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.95.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.95.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.96.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.96.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.96.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.97.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.97.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.97.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.98.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.98.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.98.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.99.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.experts.99.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.experts.99.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.gate.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00043-of-00048.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.42.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.100.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.100.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.100.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.101.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.101.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.101.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.102.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.102.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.102.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.103.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.103.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.103.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.104.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.104.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.104.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.105.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.105.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.105.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.106.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.106.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.106.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.107.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.107.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.107.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.108.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.108.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.108.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.109.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.109.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.109.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.110.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.110.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.110.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.111.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.111.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.111.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.112.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.112.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.112.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.113.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.113.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.113.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.114.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.114.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.114.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.115.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.115.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.115.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.116.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.116.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.116.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.117.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.117.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.117.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.118.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.118.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.118.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.119.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.119.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.119.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.120.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.120.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.120.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.121.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.121.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.121.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.122.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.122.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.122.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.123.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.123.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.123.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.124.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.124.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.124.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.125.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.125.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.125.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.126.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.126.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.126.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.127.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.127.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.127.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.64.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.64.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.64.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.65.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.65.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.65.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.66.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.66.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.66.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.67.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.67.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.67.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.68.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.68.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.68.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.69.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.69.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.69.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.70.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.70.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.70.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.71.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.71.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.71.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.72.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.72.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.72.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.73.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.73.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.73.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.74.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.74.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.74.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.75.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.75.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.75.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.76.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.76.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.76.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.77.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.77.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.77.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.78.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.78.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.78.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.79.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.79.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.79.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.80.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.80.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.80.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.81.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.81.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.81.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.82.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.82.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.82.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.83.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.83.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.83.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.84.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.84.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.84.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.85.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.85.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.85.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.86.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.86.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.86.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.87.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.87.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.87.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.88.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.88.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.88.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.89.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.89.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.89.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.90.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.90.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.90.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.91.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.91.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.91.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.92.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.92.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.92.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.93.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.93.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.93.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.94.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.94.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.94.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.95.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.95.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.95.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.96.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.96.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.96.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.97.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.97.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.97.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.98.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.98.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.98.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.99.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.experts.99.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.experts.99.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.gate.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00044-of-00048.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.43.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.100.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.100.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.100.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.101.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.101.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.101.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.102.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.102.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.102.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.103.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.103.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.103.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.104.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.104.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.104.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.105.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.105.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.105.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.106.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.106.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.106.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.107.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.107.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.107.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.108.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.108.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.108.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.109.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.109.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.109.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.110.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.110.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.110.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.111.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.111.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.111.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.112.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.112.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.112.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.113.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.113.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.113.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.114.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.114.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.114.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.115.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.115.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.115.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.116.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.116.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.116.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.117.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.117.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.117.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.118.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.118.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.118.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.119.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.119.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.119.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.120.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.120.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.120.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.121.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.121.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.121.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.122.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.122.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.122.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.123.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.123.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.123.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.124.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.124.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.124.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.125.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.125.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.125.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.126.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.126.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.126.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.127.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.127.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.127.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.64.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.64.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.64.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.65.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.65.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.65.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.66.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.66.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.66.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.67.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.67.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.67.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.68.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.68.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.68.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.69.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.69.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.69.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.70.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.70.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.70.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.71.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.71.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.71.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.72.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.72.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.72.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.73.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.73.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.73.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.74.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.74.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.74.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.75.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.75.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.75.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.76.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.76.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.76.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.77.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.77.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.77.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.78.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.78.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.78.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.79.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.79.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.79.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.80.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.80.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.80.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.81.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.81.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.81.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.82.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.82.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.82.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.83.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.83.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.83.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.84.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.84.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.84.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.85.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.85.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.85.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.86.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.86.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.86.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.87.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.87.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.87.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.88.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.88.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.88.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.89.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.89.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.89.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.90.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.90.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.90.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.91.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.91.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.91.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.92.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.92.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.92.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.93.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.93.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.93.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.94.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.94.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.94.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.95.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.95.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.95.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.96.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.96.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.96.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.97.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.97.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.97.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.98.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.98.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.98.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.99.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.experts.99.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.experts.99.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.gate.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00045-of-00048.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.44.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.100.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.100.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.100.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.101.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.101.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.101.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.102.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.102.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.102.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.103.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.103.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.103.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.104.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.104.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.104.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.105.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.105.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.105.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.106.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.106.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.106.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.107.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.107.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.107.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.108.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.108.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.108.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.109.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.109.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.109.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.110.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.110.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.110.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.111.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.111.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.111.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.112.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.112.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.112.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.113.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.113.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.113.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.114.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.114.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.114.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.115.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.115.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.115.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.116.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.116.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.116.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.117.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.117.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.117.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.118.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.118.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.118.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.119.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.119.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.119.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.120.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.120.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.120.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.121.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.121.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.121.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.122.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.122.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.122.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.123.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.123.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.123.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.124.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.124.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.124.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.125.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.125.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.125.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.126.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.126.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.126.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.127.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.127.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.127.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.64.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.64.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.64.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.65.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.65.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.65.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.66.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.66.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.66.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.67.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.67.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.67.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.68.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.68.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.68.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.69.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.69.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.69.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.70.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.70.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.70.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.71.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.71.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.71.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.72.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.72.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.72.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.73.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.73.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.73.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.74.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.74.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.74.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.75.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.75.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.75.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.76.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.76.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.76.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.77.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.77.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.77.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.78.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.78.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.78.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.79.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.79.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.79.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.80.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.80.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.80.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.81.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.81.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.81.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.82.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.82.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.82.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.83.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.83.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.83.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.84.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.84.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.84.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.85.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.85.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.85.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.86.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.86.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.86.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.87.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.87.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.87.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.88.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.88.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.88.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.89.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.89.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.89.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.90.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.90.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.90.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.91.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.91.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.91.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.92.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.92.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.92.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.93.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.93.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.93.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.94.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.94.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.94.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.95.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.95.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.95.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.96.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.96.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.96.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.97.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.97.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.97.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.98.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.98.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.98.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.99.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.experts.99.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.experts.99.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.gate.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00046-of-00048.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.45.input_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.100.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.100.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.100.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.101.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.101.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.101.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.102.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.102.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.102.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.103.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.103.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.103.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.104.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.104.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.104.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.105.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.105.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.105.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.106.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.106.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.106.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.107.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.107.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.107.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.108.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.108.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.108.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.109.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.109.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.109.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.110.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.110.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.110.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.111.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.111.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.111.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.112.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.112.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.112.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.113.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.113.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.113.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.114.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.114.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.114.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.115.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.115.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.115.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.116.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.116.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.116.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.117.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.117.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.117.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.118.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.118.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.118.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.119.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.119.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.119.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.120.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.120.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.120.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.121.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.121.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.121.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.122.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.122.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.122.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.123.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.123.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.123.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.124.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.124.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.124.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.125.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.125.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.125.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.126.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.126.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.126.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.127.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.127.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.127.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.64.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.64.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.64.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.65.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.65.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.65.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.66.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.66.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.66.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.67.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.67.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.67.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.68.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.68.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.68.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.69.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.69.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.69.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.70.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.70.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.70.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.71.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.71.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.71.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.72.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.72.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.72.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.73.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.73.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.73.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.74.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.74.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.74.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.75.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.75.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.75.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.76.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.76.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.76.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.77.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.77.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.77.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.78.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.78.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.78.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.79.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.79.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.79.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.80.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.80.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.80.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.81.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.81.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.81.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.82.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.82.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.82.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.83.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.83.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.83.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.84.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.84.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.84.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.85.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.85.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.85.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.86.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.86.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.86.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.87.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.87.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.87.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.88.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.88.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.88.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.89.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.89.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.89.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.90.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.90.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.90.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.91.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.91.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.91.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.92.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.92.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.92.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.93.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.93.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.93.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.94.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.94.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.94.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.95.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.95.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.95.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.96.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.96.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.96.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.97.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.97.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.97.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.98.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.98.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.98.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.99.down_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.experts.99.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.experts.99.up_proj.weight": "model-00048-of-00048.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.gate.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00047-of-00048.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00003-of-00048.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00048.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.100.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.100.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.101.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.101.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.102.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.102.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.103.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.103.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.104.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.104.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.105.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.105.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.106.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.106.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.107.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.107.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.108.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.108.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.109.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.109.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.110.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.110.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.111.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.111.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.112.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.112.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.113.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.113.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.114.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.114.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.115.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.115.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.116.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.116.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.117.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.117.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.118.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.118.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.119.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.119.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.120.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.120.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.121.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.121.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.122.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.122.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.123.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.123.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.124.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.124.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.125.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.125.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.126.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.126.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.127.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.127.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.64.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.64.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.65.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.65.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.66.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.66.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.67.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.67.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.68.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.68.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.69.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.69.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.70.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.70.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.71.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.71.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.72.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.72.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.73.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.73.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.74.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.74.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.75.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.75.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.76.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.76.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.77.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.77.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.78.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.78.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.79.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.79.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.80.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.80.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.81.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.81.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.82.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.82.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.83.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.83.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.84.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.84.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.85.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.85.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.86.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.86.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.87.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.87.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.88.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.88.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.89.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.89.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.90.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.90.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.91.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.91.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.92.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.92.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.93.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.93.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.94.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.94.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.95.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.95.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.96.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.96.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.97.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.97.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.98.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.98.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.99.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.experts.99.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.gate.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00007-of-00048.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.100.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.100.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.101.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.101.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.102.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.102.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.103.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.103.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.104.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.104.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.105.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.105.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.106.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.106.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.107.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.107.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.108.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.108.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.109.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.109.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.110.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.110.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.111.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.111.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.112.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.112.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.113.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.113.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.114.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.114.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.115.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.115.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.116.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.116.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.117.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.117.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.118.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.118.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.119.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.119.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.120.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.120.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.121.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.121.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.122.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.122.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.123.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.123.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.124.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.124.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.125.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.125.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.126.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.126.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.127.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.127.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.64.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.64.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.65.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.65.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.66.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.66.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.67.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.67.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.68.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.68.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.69.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.69.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.70.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.70.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.71.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.71.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.72.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.72.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.73.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.73.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.74.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.74.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.75.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.75.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.76.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.76.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.77.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.77.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.78.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.78.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.79.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.79.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.80.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.80.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.81.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.81.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.82.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.82.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.83.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.83.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.84.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.84.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.85.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.85.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.86.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.86.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.87.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.87.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.88.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.88.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.89.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.89.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.90.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.90.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.91.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.91.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.92.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.92.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.93.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.93.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.94.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.94.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.95.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.95.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.96.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.96.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.97.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.97.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.98.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.98.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.99.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.experts.99.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.gate.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00008-of-00048.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.100.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.100.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.101.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.101.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.102.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.102.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.103.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.103.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.104.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.104.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.105.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.105.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.106.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.106.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.107.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.107.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.108.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.108.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.109.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.109.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.110.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.110.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.111.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.111.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.112.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.112.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.113.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.113.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.114.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.114.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.115.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.115.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.116.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.116.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.117.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.117.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.118.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.118.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.119.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.119.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.120.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.120.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.121.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.121.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.122.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.122.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.123.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.123.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.124.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.124.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.125.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.125.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.126.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.126.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.127.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.127.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.64.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.64.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.65.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.65.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.66.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.66.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.67.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.67.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.68.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.68.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.69.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.69.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.70.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.70.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.71.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.71.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.72.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.72.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.73.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.73.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.74.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.74.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.75.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.75.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.76.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.76.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.77.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.77.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.78.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.78.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.79.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.79.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.80.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.80.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.81.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.81.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.82.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.82.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.83.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.83.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.84.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.84.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.85.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.85.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.86.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.86.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.87.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.87.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.88.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.88.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.89.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.89.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.90.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.90.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.91.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.91.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.92.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.92.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.93.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.93.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.94.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.94.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.95.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.95.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.96.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.96.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.97.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.97.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.98.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.98.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.99.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.experts.99.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.gate.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00009-of-00048.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.100.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.100.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.101.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.101.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.102.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.102.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.103.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.103.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.104.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.104.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.105.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.105.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.106.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.106.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.107.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.107.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.108.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.108.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.109.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.109.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.110.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.110.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.111.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.111.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.112.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.112.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.113.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.113.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.114.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.114.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.115.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.115.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.116.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.116.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.117.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.117.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.118.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.118.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.119.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.119.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.120.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.120.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.121.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.121.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.122.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.122.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.123.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.123.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.124.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.124.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.125.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.125.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.126.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.126.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.127.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.127.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.64.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.64.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.65.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.65.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.66.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.66.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.67.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.67.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.68.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.68.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.69.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.69.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.70.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.70.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.71.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.71.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.72.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.72.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.73.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.73.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.74.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.74.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.75.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.75.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.76.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.76.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.77.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.77.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.78.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.78.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.79.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.79.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.80.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.80.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.81.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.81.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.82.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.82.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.83.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.83.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.84.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.84.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.85.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.85.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.86.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.86.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.87.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.87.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.88.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.88.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.89.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.89.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.90.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.90.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.91.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.91.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.92.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.92.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.93.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.93.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.94.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.94.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.95.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.95.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.96.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.96.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.97.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.97.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.98.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.98.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.99.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.experts.99.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.gate.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00010-of-00048.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.100.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.100.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.101.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.101.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.102.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.102.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.103.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.103.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.104.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.104.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.105.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.105.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.106.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.106.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.107.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.107.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.108.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.108.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.109.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.109.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.110.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.110.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.111.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.111.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.112.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.112.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.113.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.113.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.114.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.114.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.115.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.115.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.116.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.116.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.117.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.117.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.118.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.118.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.119.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.119.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.120.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.120.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.121.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.121.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.122.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.122.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.123.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.123.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.124.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.124.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.125.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.125.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.126.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.126.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.127.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.127.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.64.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.64.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.65.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.65.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.66.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.66.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.67.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.67.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.68.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.68.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.69.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.69.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.70.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.70.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.71.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.71.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.72.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.72.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.73.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.73.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.74.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.74.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.75.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.75.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.76.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.76.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.77.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.77.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.78.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.78.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.79.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.79.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.80.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.80.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.81.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.81.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.82.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.82.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.83.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.83.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.84.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.84.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.85.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.85.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.86.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.86.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.87.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.87.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.88.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.88.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.89.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.89.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.90.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.90.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.91.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.91.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.92.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.92.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.93.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.93.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.94.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.94.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.95.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.95.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.96.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.96.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.97.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.97.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.98.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.98.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.99.down_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.experts.99.up_proj.weight": "model-00012-of-00048.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.gate.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00011-of-00048.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00048.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00048.safetensors", + "model.norm.weight": "model-00003-of-00048.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..47e7ec6fc39e9a26ea382317b9f9421fbd75f603 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,34 @@ +{ + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|im_end|>" +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..8a090ee6b8bb2f47ede5c58e267ffd79dcdfcbe5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:840a2be2f18847f07571118fb785c9bde4726991852229d98469e421bf5d1064 +size 19971076 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..f0911eb841a95c460097641c49e61a7dbf55ac33 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,341 @@ +{ + "added_tokens_decoder": { + "151329": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151330": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151331": { + "content": "[gMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151332": { + "content": "[sMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151333": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151334": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151335": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151336": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151337": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151338": { + "content": "<|observation|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151339": { + "content": "<|begin_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151340": { + "content": "<|end_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151341": { + "content": "<|begin_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151342": { + "content": "<|end_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151343": { + "content": "<|begin_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151344": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151345": { + "content": "<|begin_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151346": { + "content": "<|end_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151347": { + "content": "<|code_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151348": { + "content": "<|code_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151349": { + "content": "<|code_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151350": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151351": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151352": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151353": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151354": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151355": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151356": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151357": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151358": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151359": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151360": { + "content": "/nothink", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151361": { + "content": "<|begin_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151362": { + "content": "<|end_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151363": { + "content": "<|image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151364": { + "content": "<|video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151365": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151366": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|im_end|>", + "extra_special_tokens": {}, + "model_max_length": 128000, + "pad_token": "<|im_end|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "PreTrainedTokenizerFast" +}