diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..9a68b9c01f0cddec9f78bcfc2e6c57d1ce7cf064 --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +library_name: mlx +tags: +- prime-rl +- verifiers +- prime-intellect +- reinforcement-learning +- reasoning +- agentic +- mixture-of-experts +- mlx +license: mit +language: +- en +base_model: PrimeIntellect/INTELLECT-3 +pipeline_tag: text-generation +--- + +# mlx-community/INTELLECT-3-bf16 + +This model [mlx-community/INTELLECT-3-bf16](https://huggingface.co/mlx-community/INTELLECT-3-bf16) was +converted to MLX format from [PrimeIntellect/INTELLECT-3](https://huggingface.co/PrimeIntellect/INTELLECT-3) +using mlx-lm version **0.28.3**. + +## Use with mlx + +```bash +pip install mlx-lm +``` + +```python +from mlx_lm import load, generate + +model, tokenizer = load("mlx-community/INTELLECT-3-bf16") + +prompt = "hello" + +if tokenizer.chat_template is not None: + messages = [{"role": "user", "content": prompt}] + prompt = tokenizer.apply_chat_template( + messages, add_generation_prompt=True + ) + +response = generate(model, tokenizer, prompt=prompt, verbose=True) +``` diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..910bc4eaddb6837808614e53ce0c45f90fc83bb7 --- /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-3, a helpful assistant developed by Prime Intellect, that can interact with a computer to solve tasks." }} + {%- endif %} +{%- endif %} +{%- if tools is iterable and tools | length > 0 %} + {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }} + {{- "" }} + {%- for tool in tools %} + {%- if tool.function is defined %} + {%- set tool = tool.function %} + {%- endif %} + {{- "\n\n" ~ tool.name ~ "" }} + {%- if tool.description is defined %} + {{- '\n' ~ (tool.description | trim) ~ '' }} + {%- endif %} + {{- '\n' }} + {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %} + {%- for param_name, param_fields in tool.parameters.properties|items %} + {{- '\n' }} + {{- '\n' ~ param_name ~ '' }} + {%- if param_fields.type is defined %} + {{- '\n' ~ (param_fields.type | string) ~ '' }} + {%- endif %} + {%- if param_fields.description is defined %} + {{- '\n' ~ (param_fields.description | trim) ~ '' }} + {%- endif %} + {%- set handled_keys = ['name', 'type', 'description'] %} + {{- render_extra_keys(param_fields, handled_keys) }} + {{- '\n' }} + {%- endfor %} + {%- endif %} + {% set handled_keys = ['type', 'properties'] %} + {{- render_extra_keys(tool.parameters, handled_keys) }} + {{- '\n' }} + {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %} + {{- render_extra_keys(tool, handled_keys) }} + {{- '\n' }} + {%- endfor %} + {{- "\n" }} + {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n\n\n\nvalue_1\n\n\nThis is the value for the second parameter\nthat can span\nmultiple lines\n\n\n\n\n\nReminder:\n- Function calls MUST follow the specified format: an inner block must be nested within XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n' }} +{%- endif %} +{%- if system_message is defined %} + {{- '<|im_end|>\n' }} +{%- else %} + {%- if tools is iterable and tools | length > 0 %} + {{- '<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in loop_messages %} + {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %} + {{- '<|im_start|>' + message.role }} + {%- if message.content is defined and message.content is string %} + {%- if message.reasoning_content is defined -%} + {%- if message.reasoning_content -%} + {{ '\n' + message.reasoning_content.strip() + '' }} + {%- else -%} + {{ '\n' }} + {%- endif -%} + {%- endif -%} + {{- '\n' + message.content | trim + '\n' }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n\n' }} + {%- if tool_call.arguments is defined %} + {%- for args_name, args_value in tool_call.arguments|items %} + {{- '\n' }} + {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %} + {{- args_value }} + {{- '\n\n' }} + {%- endfor %} + {%- endif %} + {{- '\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.role == "assistant" and message.reasoning_content is defined %} + {%- if message.reasoning_content -%} + {{ '\n' + message.reasoning_content.strip() + '' }} + {%- else -%} + {{ '\n' }} + {%- endif -%} + {%- if message.content.strip() -%} + {{ '\n' + message.content.strip() }} + {%- endif -%} + {%- else %} + {{- '\n' + message.content }} + {%- endif %} + {{- '<|im_end|>' + '\n' }} + {%- elif message.role == "tool" %} + {%- if loop.previtem and loop.previtem.role != "tool" %} + {{- '<|im_start|>user\n' }} + {%- endif %} + {{- '\n' }} + {{- message.content }} + {{- '\n\n' }} + {%- if not loop.last and loop.nextitem.role != "tool" %} + {{- '<|im_end|>\n' }} + {%- elif loop.last %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- else %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..5c6c1b9fae8766d82d39f0ee80ed69679ae50cb3 --- /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 +} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..b83589cf723d21763db8020c6d30ed64936b8935 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151334, + 151329 + ], + "pad_token_id": 151329, + "transformers_version": "4.56.1", + "use_cache": false, + "temperature": 0.6 +} diff --git a/model-00002-of-00046.safetensors b/model-00002-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a440ef952bbaf590eee4964216d784a25806a8c1 --- /dev/null +++ b/model-00002-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56935253fbb17738747b142646a325ff7a3a23de556a6054e3ce947320d1de72 +size 4682988045 diff --git a/model-00003-of-00046.safetensors b/model-00003-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..326e2c53003ea930c83c52372ae7b7980d2571b4 --- /dev/null +++ b/model-00003-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de963fe19603d45fde93c950de966c827a27105a84ea43c9c560e978c02a39c7 +size 4682988045 diff --git a/model-00004-of-00046.safetensors b/model-00004-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a0ed8d136e971fb1aacbff252e057d81e3e19c1a --- /dev/null +++ b/model-00004-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b0c0ebad3c4feaf48abbc93d367ac8aea3ab2bed69381873f369311d01f16b0 +size 4682988045 diff --git a/model-00006-of-00046.safetensors b/model-00006-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8c7fc2b330849b9b1ad4ecd1e6c59a4f8f833ef2 --- /dev/null +++ b/model-00006-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7613f6a1245e2f6f20b9a4e7716a2bdc4496149cd74dbdfa426d2ff1bbbb8bcc +size 4682988041 diff --git a/model-00007-of-00046.safetensors b/model-00007-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bb9f2592861aa8f553aee82db7019e37ed287bf4 --- /dev/null +++ b/model-00007-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92d273678d9a330d8025f571d8e9ae5e68aec3f51171d4edb335a7382b022b28 +size 4682988045 diff --git a/model-00008-of-00046.safetensors b/model-00008-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..23652ea29005bccdcba63de3487fbcdefb95e472 --- /dev/null +++ b/model-00008-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f6a2506892cd9ff1969994b12cc04ed78c2f003383b5ab041d8efcdbbba66ac +size 4682988045 diff --git a/model-00009-of-00046.safetensors b/model-00009-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c29815e246de20ed724685e1374194846665d82d --- /dev/null +++ b/model-00009-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f580fbda88c304493b99dce3e7aa1e876dccc8b0d9da47cf85620eb65a5a986 +size 4682988043 diff --git a/model-00010-of-00046.safetensors b/model-00010-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..df942d28323433e776b18b592ae4b636e5162263 --- /dev/null +++ b/model-00010-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa1e402eabbc1000e696d42e6bd49032643da893d028fc0eb0fe4c310f6db76 +size 4682988054 diff --git a/model-00011-of-00046.safetensors b/model-00011-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e28aaad2a6ba77ec3ddda5f5b907a5f54cbd5a49 --- /dev/null +++ b/model-00011-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a105b9333352c1e3e33f99fad94bceec6cf96007d39dc8e2293ae9e22e196876 +size 4682988062 diff --git a/model-00012-of-00046.safetensors b/model-00012-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..775a46f2a208ba84d65680461d0f8ed703df827d --- /dev/null +++ b/model-00012-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7965c7e07f296d5d1467c5f57ddb3ed7e8e726a9d672f2808990d7db620ae886 +size 4682988062 diff --git a/model-00013-of-00046.safetensors b/model-00013-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..acbe8a0e385e17286e91a66a0311048322a55f26 --- /dev/null +++ b/model-00013-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:371e66dcfec48be5b9973c079310408d8d50679dec0c572e3590037f69c44193 +size 4682988058 diff --git a/model-00014-of-00046.safetensors b/model-00014-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6df1e5db17c2f387e61b46880d0edc1925386a5a --- /dev/null +++ b/model-00014-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d72eb59515d84d6e3098543e0954c88849db48a828a8860f7d8516807bebb747 +size 4682988062 diff --git a/model-00015-of-00046.safetensors b/model-00015-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e29ceda5bdad862f1a90f922708dadf8003c43b --- /dev/null +++ b/model-00015-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a6320c30c1530687309e284d8e6a300b286fd405ad6a17d76b5be73dfecb246 +size 4682988062 diff --git a/model-00016-of-00046.safetensors b/model-00016-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c7642d94ae9c9b4745f860af5c11cdc9d19c59f5 --- /dev/null +++ b/model-00016-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e2ec969d47994d4aa885cd171cee675c93846c1c8f4891b97b869496b023fbf +size 4682988062 diff --git a/model-00017-of-00046.safetensors b/model-00017-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..17bf2e8e108046b48b8fb986c8422bcb2b4f0d97 --- /dev/null +++ b/model-00017-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5da7fb7406a05b4e39e29f60bd3f1513f7429db3a080fcf45546f0d3843cba3b +size 4682988062 diff --git a/model-00018-of-00046.safetensors b/model-00018-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6882714aba3fb45dd7e194d7d5164ef9f7020198 --- /dev/null +++ b/model-00018-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a79dbcb6ccbb30f8063043a6532ca328bed9691ad81ed7780521080033142d6f +size 4682988062 diff --git a/model-00019-of-00046.safetensors b/model-00019-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4c57dd734c5637a53c6bddc6105e94884cd37528 --- /dev/null +++ b/model-00019-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ffc268247b756c1cbe4a80414a5b7e6a52cf8fbf8325d46d3319bc051798016 +size 4682988062 diff --git a/model-00020-of-00046.safetensors b/model-00020-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..859f4ec635852c1165512749c8a89d6955d100ba --- /dev/null +++ b/model-00020-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:569a7403c3d358c01cc70ed46efa3be0b27f92d406ec9bffd059a3d3ed18d165 +size 4682988062 diff --git a/model-00022-of-00046.safetensors b/model-00022-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9cc4ac0ee5af534a99618234373548dd0498095a --- /dev/null +++ b/model-00022-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:552605f1085903e482e1944ae1231819b2c750c7bf35fca81da9ad89a2395cad +size 4682988062 diff --git a/model-00023-of-00046.safetensors b/model-00023-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..64cff702c5c59acbe0cd3781c5917c218d76c11a --- /dev/null +++ b/model-00023-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b584d002fb4479e3d6034470fe2da48f3cdc2a16471fbeb0114cb9847d705df +size 4682988062 diff --git a/model-00024-of-00046.safetensors b/model-00024-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e96419b9b3c45a3aa5c7de4c4d660fb04b558cca --- /dev/null +++ b/model-00024-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db64e11d41022cb70f7052726359c7ecb0a10a8764cd8f06b79896200d4f28d3 +size 4682988062 diff --git a/model-00025-of-00046.safetensors b/model-00025-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..12162627a7302cf330c076450a28cd85578f423d --- /dev/null +++ b/model-00025-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cddbeee3c1a8c0c2b0055aadd716a9195174fc955aa84f1f302e572daa38f3b +size 4682988062 diff --git a/model-00026-of-00046.safetensors b/model-00026-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..29a7363cdd5a24e4aea8231fb3785790f71bfc20 --- /dev/null +++ b/model-00026-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c3411d57caeb0a35f412ddb82abf7b3048a734875ca790cbbfbcca13149aecd +size 4682988062 diff --git a/model-00027-of-00046.safetensors b/model-00027-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e46f7880e44e9dcf090863bbc66f763000403eb1 --- /dev/null +++ b/model-00027-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63a09bbff6d33a83ebb0549580dd12c997f824c22c5311c4587eab6a4f2ebd5 +size 4682988062 diff --git a/model-00028-of-00046.safetensors b/model-00028-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8ef1694ece3d472c9140919e11aef352c9721adb --- /dev/null +++ b/model-00028-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9432acef7271b1603abc1ad957186b28c562a94b0b0b42ba6203c3728c32f3af +size 4682988062 diff --git a/model-00029-of-00046.safetensors b/model-00029-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d5385c671c29fa243fde92dd2ff9806a5e9476e2 --- /dev/null +++ b/model-00029-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e88608fa1a8a7b01fef1b5966a9f15c38b1b3509ac03b3a74636ea743957e203 +size 4682988062 diff --git a/model-00030-of-00046.safetensors b/model-00030-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..af2d146e1a0f0411b74713c44f55fd0308b04c25 --- /dev/null +++ b/model-00030-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b77f9bdeca85bc0a14d24976b4c5d19bd80a810961eceae420feb3065767e9 +size 4682988062 diff --git a/model-00031-of-00046.safetensors b/model-00031-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a48164cd302024297b813d676f77ab5db36a871b --- /dev/null +++ b/model-00031-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30b58a6a04d0811c19e9796cf8df2f6fe04420bccad0980eaf35b8fe2c73f173 +size 4682988062 diff --git a/model-00032-of-00046.safetensors b/model-00032-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cb7551c0ac68663eee89270f90eb6d243e87be6d --- /dev/null +++ b/model-00032-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6802339cf4221a44e536601e7a7015cff7c872890154b1ff214af88b7db17908 +size 4682988062 diff --git a/model-00033-of-00046.safetensors b/model-00033-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ca4066e244fd0e2ccb51e3e7f71cfce75c630f2 --- /dev/null +++ b/model-00033-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2245dffd273b869b21203f389d79fa870cae63498dab757dea158cbc989f54f2 +size 4682988062 diff --git a/model-00034-of-00046.safetensors b/model-00034-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b25b1b66cfa0d2df4e74a60dba34612273de285 --- /dev/null +++ b/model-00034-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b9998309678d97a46c4bbd2eac42a8b6053552bd4ed37f51a105f1b33c61ed6 +size 4682988062 diff --git a/model-00035-of-00046.safetensors b/model-00035-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7603e7501c913e6e1924e8986538d93b92888765 --- /dev/null +++ b/model-00035-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c41d8cbddb385eb30f2b8cbc895111c167a2ff660a2c3063a8bfcb0b5ea3d735 +size 4682988062 diff --git a/model-00036-of-00046.safetensors b/model-00036-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a6a3d15781f9f0fe5ecab29baa392c15ac367ed --- /dev/null +++ b/model-00036-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7289867855a521d168afc87df11c81c26e6126f824d0ae00c06461024b79e5ae +size 4682988062 diff --git a/model-00037-of-00046.safetensors b/model-00037-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d689775ea5efb021f16cd2680c99864835eca59 --- /dev/null +++ b/model-00037-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9ec21a92c992dc7600d32f74f76f5fbeeb527c0b130e3e6da1dd747558815b8 +size 4682988062 diff --git a/model-00038-of-00046.safetensors b/model-00038-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e2e9a2865f2bcb860178a8a04867690b7fbfe484 --- /dev/null +++ b/model-00038-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d6bda1cdb0598c54340ac25889ad5d0b6baca3948dcd195a68fdbb3fd8eecae +size 4682988062 diff --git a/model-00039-of-00046.safetensors b/model-00039-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..97e747af4f54c72639d32bce9347dcb644a4d074 --- /dev/null +++ b/model-00039-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60348863c640ff16025919f58acc73742dc53a6cd954322b6979e53cce5a5691 +size 4682988062 diff --git a/model-00040-of-00046.safetensors b/model-00040-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f1aab8a12eacfd08ca42c3f456dc6ce15e837c49 --- /dev/null +++ b/model-00040-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62dc5ddf08db50211f809b08a51cc6613bfc08e05d431ea6e36c2ce833057b52 +size 4682988058 diff --git a/model-00042-of-00046.safetensors b/model-00042-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db37fc98e8153ac4ef8ad67c60ce4dbe9ecfd9b2 --- /dev/null +++ b/model-00042-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84600a0fa800a0be76a1f5f05d4ecfbcf27acb58a653dd83bbae4bd9b4623680 +size 4682988062 diff --git a/model-00043-of-00046.safetensors b/model-00043-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fad959e06e31234a7327434c97e599192421fdfd --- /dev/null +++ b/model-00043-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e71d85a049b2d0dcc9e768a39d87c493fb3d2b13e7840fd366f66363353818 +size 4682988062 diff --git a/model-00044-of-00046.safetensors b/model-00044-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b1ae29afd2b6bcaccfc9d9ee5a78873ea98ff0ea --- /dev/null +++ b/model-00044-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:892cc5acb2e01969116889ff5b38af955308036056efdee29e9e71b89c091a51 +size 4682988062 diff --git a/model-00045-of-00046.safetensors b/model-00045-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cba54c8f9e60456a35a9151c7119b90b1e5e1d58 --- /dev/null +++ b/model-00045-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1a215ffa1a130cddf2fd6938780cf464af70333a3eb413d7102f6f1672929b2 +size 4682988062 diff --git a/model-00046-of-00046.safetensors b/model-00046-of-00046.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..259d5a42473e456e61a6ae03cc5e7b12a3f4e89b --- /dev/null +++ b/model-00046-of-00046.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d8ee562d842542cfffc115c6ecdde9b3ef60e8ae97e4c15b9b91c25199ac5cf +size 2753586862 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..1d9c3fd0022eaa2316551f4c2214a107c8b2b572 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,788 @@ +{ + "metadata": { + "total_size": 213704514048, + "total_parameters": 106852251264 + }, + "weight_map": { + "lm_head.weight": "model-00046-of-00046.safetensors", + "model.embed_tokens.weight": "model-00001-of-00046.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00046.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00046.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00046.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00046.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00046.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00046.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00046.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00046.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00046.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00046.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00046.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00046.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00046.safetensors", + "model.layers.1.mlp.gate.e_score_correction_bias": "model-00002-of-00046.safetensors", + "model.layers.1.mlp.gate.weight": "model-00002-of-00046.safetensors", + "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00002-of-00046.safetensors", + "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00002-of-00046.safetensors", + "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00002-of-00046.safetensors", + "model.layers.1.mlp.switch_mlp.down_proj.weight": "model-00002-of-00046.safetensors", + "model.layers.1.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00046.safetensors", + "model.layers.1.mlp.switch_mlp.up_proj.weight": "model-00001-of-00046.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00046.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00046.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00046.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00046.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00046.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00046.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00046.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00046.safetensors", + "model.layers.10.input_layernorm.weight": "model-00011-of-00046.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00011-of-00046.safetensors", + "model.layers.10.mlp.gate.weight": "model-00011-of-00046.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00011-of-00046.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00011-of-00046.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00011-of-00046.safetensors", + "model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00011-of-00046.safetensors", + "model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00046.safetensors", + "model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00010-of-00046.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00046.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00010-of-00046.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00046.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00010-of-00046.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00010-of-00046.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00046.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00010-of-00046.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00010-of-00046.safetensors", + "model.layers.11.input_layernorm.weight": "model-00012-of-00046.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00012-of-00046.safetensors", + "model.layers.11.mlp.gate.weight": "model-00012-of-00046.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00012-of-00046.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00012-of-00046.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00012-of-00046.safetensors", + "model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00012-of-00046.safetensors", + "model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00046.safetensors", + "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00011-of-00046.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00012-of-00046.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00011-of-00046.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00011-of-00046.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00011-of-00046.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00011-of-00046.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00011-of-00046.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00011-of-00046.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00011-of-00046.safetensors", + "model.layers.12.input_layernorm.weight": "model-00013-of-00046.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00013-of-00046.safetensors", + "model.layers.12.mlp.gate.weight": "model-00013-of-00046.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00013-of-00046.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00013-of-00046.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00013-of-00046.safetensors", + "model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00013-of-00046.safetensors", + "model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00046.safetensors", + "model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00012-of-00046.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00013-of-00046.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00012-of-00046.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00012-of-00046.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00012-of-00046.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00012-of-00046.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00012-of-00046.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00012-of-00046.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00012-of-00046.safetensors", + "model.layers.13.input_layernorm.weight": "model-00014-of-00046.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00014-of-00046.safetensors", + "model.layers.13.mlp.gate.weight": "model-00014-of-00046.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00014-of-00046.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00014-of-00046.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00014-of-00046.safetensors", + "model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00014-of-00046.safetensors", + "model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00046.safetensors", + "model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00013-of-00046.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00014-of-00046.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00013-of-00046.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00013-of-00046.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00013-of-00046.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00013-of-00046.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00013-of-00046.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00013-of-00046.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00013-of-00046.safetensors", + "model.layers.14.input_layernorm.weight": "model-00015-of-00046.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00015-of-00046.safetensors", + "model.layers.14.mlp.gate.weight": "model-00015-of-00046.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00015-of-00046.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00015-of-00046.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00015-of-00046.safetensors", + "model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00015-of-00046.safetensors", + "model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00046.safetensors", + "model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00014-of-00046.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00015-of-00046.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00014-of-00046.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00014-of-00046.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00014-of-00046.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00014-of-00046.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00014-of-00046.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00014-of-00046.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00014-of-00046.safetensors", + "model.layers.15.input_layernorm.weight": "model-00016-of-00046.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00016-of-00046.safetensors", + "model.layers.15.mlp.gate.weight": "model-00016-of-00046.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00016-of-00046.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00016-of-00046.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00016-of-00046.safetensors", + "model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00016-of-00046.safetensors", + "model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00046.safetensors", + "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00015-of-00046.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00016-of-00046.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00015-of-00046.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00015-of-00046.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00015-of-00046.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00015-of-00046.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00015-of-00046.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00015-of-00046.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00015-of-00046.safetensors", + "model.layers.16.input_layernorm.weight": "model-00017-of-00046.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00017-of-00046.safetensors", + "model.layers.16.mlp.gate.weight": "model-00017-of-00046.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00017-of-00046.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00017-of-00046.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00017-of-00046.safetensors", + "model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00017-of-00046.safetensors", + "model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00016-of-00046.safetensors", + "model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00016-of-00046.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00017-of-00046.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00016-of-00046.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00016-of-00046.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00016-of-00046.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00016-of-00046.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00016-of-00046.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00016-of-00046.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00016-of-00046.safetensors", + "model.layers.17.input_layernorm.weight": "model-00018-of-00046.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00018-of-00046.safetensors", + "model.layers.17.mlp.gate.weight": "model-00018-of-00046.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00018-of-00046.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00018-of-00046.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00018-of-00046.safetensors", + "model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00018-of-00046.safetensors", + "model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00046.safetensors", + "model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00017-of-00046.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00018-of-00046.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00017-of-00046.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00017-of-00046.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00017-of-00046.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00017-of-00046.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00017-of-00046.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00017-of-00046.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00017-of-00046.safetensors", + "model.layers.18.input_layernorm.weight": "model-00019-of-00046.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00019-of-00046.safetensors", + "model.layers.18.mlp.gate.weight": "model-00019-of-00046.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00019-of-00046.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00019-of-00046.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00019-of-00046.safetensors", + "model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00019-of-00046.safetensors", + "model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00018-of-00046.safetensors", + "model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00018-of-00046.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00019-of-00046.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00018-of-00046.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00018-of-00046.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00018-of-00046.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00018-of-00046.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00018-of-00046.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00018-of-00046.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00018-of-00046.safetensors", + "model.layers.19.input_layernorm.weight": "model-00020-of-00046.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00020-of-00046.safetensors", + "model.layers.19.mlp.gate.weight": "model-00020-of-00046.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00020-of-00046.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00020-of-00046.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00020-of-00046.safetensors", + "model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00020-of-00046.safetensors", + "model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00019-of-00046.safetensors", + "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00019-of-00046.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00020-of-00046.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00019-of-00046.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00019-of-00046.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00019-of-00046.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00019-of-00046.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00019-of-00046.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00019-of-00046.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00019-of-00046.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00046.safetensors", + "model.layers.2.mlp.gate.e_score_correction_bias": "model-00003-of-00046.safetensors", + "model.layers.2.mlp.gate.weight": "model-00003-of-00046.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00003-of-00046.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00003-of-00046.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00003-of-00046.safetensors", + "model.layers.2.mlp.switch_mlp.down_proj.weight": "model-00003-of-00046.safetensors", + "model.layers.2.mlp.switch_mlp.gate_proj.weight": "model-00002-of-00046.safetensors", + "model.layers.2.mlp.switch_mlp.up_proj.weight": "model-00002-of-00046.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00046.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00046.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00046.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00046.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00046.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00046.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00046.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00046.safetensors", + "model.layers.20.input_layernorm.weight": "model-00021-of-00046.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00021-of-00046.safetensors", + "model.layers.20.mlp.gate.weight": "model-00021-of-00046.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00021-of-00046.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00021-of-00046.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00021-of-00046.safetensors", + "model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00021-of-00046.safetensors", + "model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00046.safetensors", + "model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00020-of-00046.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00021-of-00046.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00020-of-00046.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00020-of-00046.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00020-of-00046.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00020-of-00046.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00020-of-00046.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00020-of-00046.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00020-of-00046.safetensors", + "model.layers.21.input_layernorm.weight": "model-00022-of-00046.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00022-of-00046.safetensors", + "model.layers.21.mlp.gate.weight": "model-00022-of-00046.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00022-of-00046.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00022-of-00046.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00022-of-00046.safetensors", + "model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00022-of-00046.safetensors", + "model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00021-of-00046.safetensors", + "model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00021-of-00046.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00022-of-00046.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00021-of-00046.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00021-of-00046.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00021-of-00046.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00021-of-00046.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00021-of-00046.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00021-of-00046.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00021-of-00046.safetensors", + "model.layers.22.input_layernorm.weight": "model-00023-of-00046.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00023-of-00046.safetensors", + "model.layers.22.mlp.gate.weight": "model-00023-of-00046.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00023-of-00046.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00023-of-00046.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00023-of-00046.safetensors", + "model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00023-of-00046.safetensors", + "model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00022-of-00046.safetensors", + "model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00022-of-00046.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00023-of-00046.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00022-of-00046.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00022-of-00046.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00022-of-00046.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00022-of-00046.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00022-of-00046.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00022-of-00046.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00022-of-00046.safetensors", + "model.layers.23.input_layernorm.weight": "model-00024-of-00046.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00024-of-00046.safetensors", + "model.layers.23.mlp.gate.weight": "model-00024-of-00046.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00024-of-00046.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00024-of-00046.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00024-of-00046.safetensors", + "model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00024-of-00046.safetensors", + "model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00046.safetensors", + "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00023-of-00046.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00024-of-00046.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00023-of-00046.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00023-of-00046.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00023-of-00046.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00023-of-00046.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00023-of-00046.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00023-of-00046.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00023-of-00046.safetensors", + "model.layers.24.input_layernorm.weight": "model-00025-of-00046.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00025-of-00046.safetensors", + "model.layers.24.mlp.gate.weight": "model-00025-of-00046.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00025-of-00046.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00025-of-00046.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00025-of-00046.safetensors", + "model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00025-of-00046.safetensors", + "model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00024-of-00046.safetensors", + "model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00024-of-00046.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00025-of-00046.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00024-of-00046.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00024-of-00046.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00024-of-00046.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00024-of-00046.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00024-of-00046.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00024-of-00046.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00024-of-00046.safetensors", + "model.layers.25.input_layernorm.weight": "model-00026-of-00046.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00026-of-00046.safetensors", + "model.layers.25.mlp.gate.weight": "model-00026-of-00046.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00026-of-00046.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00026-of-00046.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00026-of-00046.safetensors", + "model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00026-of-00046.safetensors", + "model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00025-of-00046.safetensors", + "model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00025-of-00046.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00026-of-00046.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00025-of-00046.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00025-of-00046.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00025-of-00046.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00025-of-00046.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00025-of-00046.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00025-of-00046.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00025-of-00046.safetensors", + "model.layers.26.input_layernorm.weight": "model-00027-of-00046.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00027-of-00046.safetensors", + "model.layers.26.mlp.gate.weight": "model-00027-of-00046.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00027-of-00046.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00027-of-00046.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00027-of-00046.safetensors", + "model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00027-of-00046.safetensors", + "model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00026-of-00046.safetensors", + "model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00026-of-00046.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00027-of-00046.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00026-of-00046.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00026-of-00046.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00026-of-00046.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00026-of-00046.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00026-of-00046.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00026-of-00046.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00026-of-00046.safetensors", + "model.layers.27.input_layernorm.weight": "model-00028-of-00046.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00028-of-00046.safetensors", + "model.layers.27.mlp.gate.weight": "model-00028-of-00046.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00028-of-00046.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00028-of-00046.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00028-of-00046.safetensors", + "model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00028-of-00046.safetensors", + "model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00027-of-00046.safetensors", + "model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00027-of-00046.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00028-of-00046.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00027-of-00046.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00027-of-00046.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00027-of-00046.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00027-of-00046.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00027-of-00046.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00027-of-00046.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00027-of-00046.safetensors", + "model.layers.28.input_layernorm.weight": "model-00029-of-00046.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00029-of-00046.safetensors", + "model.layers.28.mlp.gate.weight": "model-00029-of-00046.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00029-of-00046.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00029-of-00046.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00029-of-00046.safetensors", + "model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00029-of-00046.safetensors", + "model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00028-of-00046.safetensors", + "model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00028-of-00046.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00029-of-00046.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00028-of-00046.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00028-of-00046.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00028-of-00046.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00028-of-00046.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00028-of-00046.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00028-of-00046.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00028-of-00046.safetensors", + "model.layers.29.input_layernorm.weight": "model-00030-of-00046.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00030-of-00046.safetensors", + "model.layers.29.mlp.gate.weight": "model-00030-of-00046.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00030-of-00046.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00030-of-00046.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00030-of-00046.safetensors", + "model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00030-of-00046.safetensors", + "model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00029-of-00046.safetensors", + "model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00029-of-00046.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00030-of-00046.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00029-of-00046.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00029-of-00046.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00029-of-00046.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00029-of-00046.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00029-of-00046.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00029-of-00046.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00029-of-00046.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00046.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00004-of-00046.safetensors", + "model.layers.3.mlp.gate.weight": "model-00004-of-00046.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00004-of-00046.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00004-of-00046.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00004-of-00046.safetensors", + "model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00004-of-00046.safetensors", + "model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00003-of-00046.safetensors", + "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00003-of-00046.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00046.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00046.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00046.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00046.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00046.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00046.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00046.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00046.safetensors", + "model.layers.30.input_layernorm.weight": "model-00031-of-00046.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00031-of-00046.safetensors", + "model.layers.30.mlp.gate.weight": "model-00031-of-00046.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00031-of-00046.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00031-of-00046.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00031-of-00046.safetensors", + "model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00031-of-00046.safetensors", + "model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00030-of-00046.safetensors", + "model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00030-of-00046.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00031-of-00046.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00030-of-00046.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00030-of-00046.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00030-of-00046.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00030-of-00046.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00030-of-00046.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00030-of-00046.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00030-of-00046.safetensors", + "model.layers.31.input_layernorm.weight": "model-00032-of-00046.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00032-of-00046.safetensors", + "model.layers.31.mlp.gate.weight": "model-00032-of-00046.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00032-of-00046.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00032-of-00046.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00032-of-00046.safetensors", + "model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00032-of-00046.safetensors", + "model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00031-of-00046.safetensors", + "model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00031-of-00046.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00032-of-00046.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00031-of-00046.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00031-of-00046.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00031-of-00046.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00031-of-00046.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00031-of-00046.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00031-of-00046.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00031-of-00046.safetensors", + "model.layers.32.input_layernorm.weight": "model-00033-of-00046.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00033-of-00046.safetensors", + "model.layers.32.mlp.gate.weight": "model-00033-of-00046.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00033-of-00046.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00033-of-00046.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00033-of-00046.safetensors", + "model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00033-of-00046.safetensors", + "model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00032-of-00046.safetensors", + "model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00032-of-00046.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00033-of-00046.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00032-of-00046.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00032-of-00046.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00032-of-00046.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00032-of-00046.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00032-of-00046.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00032-of-00046.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00032-of-00046.safetensors", + "model.layers.33.input_layernorm.weight": "model-00034-of-00046.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00034-of-00046.safetensors", + "model.layers.33.mlp.gate.weight": "model-00034-of-00046.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00034-of-00046.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00034-of-00046.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00034-of-00046.safetensors", + "model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00034-of-00046.safetensors", + "model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00033-of-00046.safetensors", + "model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00033-of-00046.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00034-of-00046.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00033-of-00046.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00033-of-00046.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00033-of-00046.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00033-of-00046.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00033-of-00046.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00033-of-00046.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00033-of-00046.safetensors", + "model.layers.34.input_layernorm.weight": "model-00035-of-00046.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00035-of-00046.safetensors", + "model.layers.34.mlp.gate.weight": "model-00035-of-00046.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00035-of-00046.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00035-of-00046.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00035-of-00046.safetensors", + "model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00035-of-00046.safetensors", + "model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00034-of-00046.safetensors", + "model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00034-of-00046.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00035-of-00046.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00034-of-00046.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00034-of-00046.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00034-of-00046.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00034-of-00046.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00034-of-00046.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00034-of-00046.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00034-of-00046.safetensors", + "model.layers.35.input_layernorm.weight": "model-00036-of-00046.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00036-of-00046.safetensors", + "model.layers.35.mlp.gate.weight": "model-00036-of-00046.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00036-of-00046.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00036-of-00046.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00036-of-00046.safetensors", + "model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00036-of-00046.safetensors", + "model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00035-of-00046.safetensors", + "model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00035-of-00046.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00036-of-00046.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00035-of-00046.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00035-of-00046.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00035-of-00046.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00035-of-00046.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00035-of-00046.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00035-of-00046.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00035-of-00046.safetensors", + "model.layers.36.input_layernorm.weight": "model-00037-of-00046.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00037-of-00046.safetensors", + "model.layers.36.mlp.gate.weight": "model-00037-of-00046.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00037-of-00046.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00037-of-00046.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00037-of-00046.safetensors", + "model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00037-of-00046.safetensors", + "model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00036-of-00046.safetensors", + "model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00036-of-00046.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00037-of-00046.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00036-of-00046.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00036-of-00046.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00036-of-00046.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00036-of-00046.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00036-of-00046.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00036-of-00046.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00036-of-00046.safetensors", + "model.layers.37.input_layernorm.weight": "model-00038-of-00046.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00038-of-00046.safetensors", + "model.layers.37.mlp.gate.weight": "model-00038-of-00046.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00038-of-00046.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00038-of-00046.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00038-of-00046.safetensors", + "model.layers.37.mlp.switch_mlp.down_proj.weight": "model-00038-of-00046.safetensors", + "model.layers.37.mlp.switch_mlp.gate_proj.weight": "model-00037-of-00046.safetensors", + "model.layers.37.mlp.switch_mlp.up_proj.weight": "model-00037-of-00046.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00038-of-00046.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00037-of-00046.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00037-of-00046.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00037-of-00046.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00037-of-00046.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00037-of-00046.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00037-of-00046.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00037-of-00046.safetensors", + "model.layers.38.input_layernorm.weight": "model-00039-of-00046.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00039-of-00046.safetensors", + "model.layers.38.mlp.gate.weight": "model-00039-of-00046.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00039-of-00046.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00039-of-00046.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00039-of-00046.safetensors", + "model.layers.38.mlp.switch_mlp.down_proj.weight": "model-00039-of-00046.safetensors", + "model.layers.38.mlp.switch_mlp.gate_proj.weight": "model-00038-of-00046.safetensors", + "model.layers.38.mlp.switch_mlp.up_proj.weight": "model-00038-of-00046.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00039-of-00046.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00038-of-00046.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00038-of-00046.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00038-of-00046.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00038-of-00046.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00038-of-00046.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00038-of-00046.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00038-of-00046.safetensors", + "model.layers.39.input_layernorm.weight": "model-00040-of-00046.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00040-of-00046.safetensors", + "model.layers.39.mlp.gate.weight": "model-00040-of-00046.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00040-of-00046.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00040-of-00046.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00040-of-00046.safetensors", + "model.layers.39.mlp.switch_mlp.down_proj.weight": "model-00040-of-00046.safetensors", + "model.layers.39.mlp.switch_mlp.gate_proj.weight": "model-00039-of-00046.safetensors", + "model.layers.39.mlp.switch_mlp.up_proj.weight": "model-00039-of-00046.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00040-of-00046.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00039-of-00046.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00039-of-00046.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00039-of-00046.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00039-of-00046.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00039-of-00046.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00039-of-00046.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00039-of-00046.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00046.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00005-of-00046.safetensors", + "model.layers.4.mlp.gate.weight": "model-00005-of-00046.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00005-of-00046.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00005-of-00046.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00005-of-00046.safetensors", + "model.layers.4.mlp.switch_mlp.down_proj.weight": "model-00005-of-00046.safetensors", + "model.layers.4.mlp.switch_mlp.gate_proj.weight": "model-00004-of-00046.safetensors", + "model.layers.4.mlp.switch_mlp.up_proj.weight": "model-00004-of-00046.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00046.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00004-of-00046.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00046.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00046.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00004-of-00046.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00046.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00004-of-00046.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00046.safetensors", + "model.layers.40.input_layernorm.weight": "model-00041-of-00046.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00041-of-00046.safetensors", + "model.layers.40.mlp.gate.weight": "model-00041-of-00046.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00041-of-00046.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00041-of-00046.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00041-of-00046.safetensors", + "model.layers.40.mlp.switch_mlp.down_proj.weight": "model-00041-of-00046.safetensors", + "model.layers.40.mlp.switch_mlp.gate_proj.weight": "model-00040-of-00046.safetensors", + "model.layers.40.mlp.switch_mlp.up_proj.weight": "model-00040-of-00046.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00041-of-00046.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00040-of-00046.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00040-of-00046.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00040-of-00046.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00040-of-00046.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00040-of-00046.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00040-of-00046.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00040-of-00046.safetensors", + "model.layers.41.input_layernorm.weight": "model-00042-of-00046.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00042-of-00046.safetensors", + "model.layers.41.mlp.gate.weight": "model-00042-of-00046.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00042-of-00046.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00042-of-00046.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00042-of-00046.safetensors", + "model.layers.41.mlp.switch_mlp.down_proj.weight": "model-00042-of-00046.safetensors", + "model.layers.41.mlp.switch_mlp.gate_proj.weight": "model-00041-of-00046.safetensors", + "model.layers.41.mlp.switch_mlp.up_proj.weight": "model-00041-of-00046.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00042-of-00046.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00041-of-00046.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00041-of-00046.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00041-of-00046.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00041-of-00046.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00041-of-00046.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00041-of-00046.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00041-of-00046.safetensors", + "model.layers.42.input_layernorm.weight": "model-00043-of-00046.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00043-of-00046.safetensors", + "model.layers.42.mlp.gate.weight": "model-00043-of-00046.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00043-of-00046.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00043-of-00046.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00043-of-00046.safetensors", + "model.layers.42.mlp.switch_mlp.down_proj.weight": "model-00043-of-00046.safetensors", + "model.layers.42.mlp.switch_mlp.gate_proj.weight": "model-00042-of-00046.safetensors", + "model.layers.42.mlp.switch_mlp.up_proj.weight": "model-00042-of-00046.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00043-of-00046.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00042-of-00046.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00042-of-00046.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00042-of-00046.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00042-of-00046.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00042-of-00046.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00042-of-00046.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00042-of-00046.safetensors", + "model.layers.43.input_layernorm.weight": "model-00044-of-00046.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00044-of-00046.safetensors", + "model.layers.43.mlp.gate.weight": "model-00044-of-00046.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00044-of-00046.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00044-of-00046.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00044-of-00046.safetensors", + "model.layers.43.mlp.switch_mlp.down_proj.weight": "model-00044-of-00046.safetensors", + "model.layers.43.mlp.switch_mlp.gate_proj.weight": "model-00043-of-00046.safetensors", + "model.layers.43.mlp.switch_mlp.up_proj.weight": "model-00043-of-00046.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00044-of-00046.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00043-of-00046.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00043-of-00046.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00043-of-00046.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00043-of-00046.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00043-of-00046.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00043-of-00046.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00043-of-00046.safetensors", + "model.layers.44.input_layernorm.weight": "model-00045-of-00046.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00045-of-00046.safetensors", + "model.layers.44.mlp.gate.weight": "model-00045-of-00046.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00045-of-00046.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00045-of-00046.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00045-of-00046.safetensors", + "model.layers.44.mlp.switch_mlp.down_proj.weight": "model-00045-of-00046.safetensors", + "model.layers.44.mlp.switch_mlp.gate_proj.weight": "model-00044-of-00046.safetensors", + "model.layers.44.mlp.switch_mlp.up_proj.weight": "model-00044-of-00046.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00045-of-00046.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00044-of-00046.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00044-of-00046.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00044-of-00046.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00044-of-00046.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00044-of-00046.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00044-of-00046.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00044-of-00046.safetensors", + "model.layers.45.input_layernorm.weight": "model-00046-of-00046.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00046-of-00046.safetensors", + "model.layers.45.mlp.gate.weight": "model-00046-of-00046.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00046-of-00046.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00046-of-00046.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00046-of-00046.safetensors", + "model.layers.45.mlp.switch_mlp.down_proj.weight": "model-00046-of-00046.safetensors", + "model.layers.45.mlp.switch_mlp.gate_proj.weight": "model-00045-of-00046.safetensors", + "model.layers.45.mlp.switch_mlp.up_proj.weight": "model-00045-of-00046.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00046-of-00046.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00045-of-00046.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00045-of-00046.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00045-of-00046.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00045-of-00046.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00045-of-00046.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00045-of-00046.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00045-of-00046.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00046.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00006-of-00046.safetensors", + "model.layers.5.mlp.gate.weight": "model-00006-of-00046.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00006-of-00046.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00006-of-00046.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00006-of-00046.safetensors", + "model.layers.5.mlp.switch_mlp.down_proj.weight": "model-00006-of-00046.safetensors", + "model.layers.5.mlp.switch_mlp.gate_proj.weight": "model-00005-of-00046.safetensors", + "model.layers.5.mlp.switch_mlp.up_proj.weight": "model-00005-of-00046.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00046.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00005-of-00046.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00046.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00046.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00005-of-00046.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00046.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00005-of-00046.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00046.safetensors", + "model.layers.6.input_layernorm.weight": "model-00007-of-00046.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00007-of-00046.safetensors", + "model.layers.6.mlp.gate.weight": "model-00007-of-00046.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00007-of-00046.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00007-of-00046.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00007-of-00046.safetensors", + "model.layers.6.mlp.switch_mlp.down_proj.weight": "model-00007-of-00046.safetensors", + "model.layers.6.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00046.safetensors", + "model.layers.6.mlp.switch_mlp.up_proj.weight": "model-00006-of-00046.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00046.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00006-of-00046.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00046.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00046.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00006-of-00046.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00046.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00006-of-00046.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00046.safetensors", + "model.layers.7.input_layernorm.weight": "model-00008-of-00046.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00008-of-00046.safetensors", + "model.layers.7.mlp.gate.weight": "model-00008-of-00046.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00008-of-00046.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00008-of-00046.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00008-of-00046.safetensors", + "model.layers.7.mlp.switch_mlp.down_proj.weight": "model-00008-of-00046.safetensors", + "model.layers.7.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00046.safetensors", + "model.layers.7.mlp.switch_mlp.up_proj.weight": "model-00007-of-00046.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00046.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00007-of-00046.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00046.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00046.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00007-of-00046.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00046.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00007-of-00046.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00046.safetensors", + "model.layers.8.input_layernorm.weight": "model-00009-of-00046.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00009-of-00046.safetensors", + "model.layers.8.mlp.gate.weight": "model-00009-of-00046.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00009-of-00046.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00009-of-00046.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00009-of-00046.safetensors", + "model.layers.8.mlp.switch_mlp.down_proj.weight": "model-00009-of-00046.safetensors", + "model.layers.8.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00046.safetensors", + "model.layers.8.mlp.switch_mlp.up_proj.weight": "model-00008-of-00046.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00046.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00008-of-00046.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00046.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00046.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00008-of-00046.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00046.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00008-of-00046.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00046.safetensors", + "model.layers.9.input_layernorm.weight": "model-00010-of-00046.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00010-of-00046.safetensors", + "model.layers.9.mlp.gate.weight": "model-00010-of-00046.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00010-of-00046.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00010-of-00046.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00010-of-00046.safetensors", + "model.layers.9.mlp.switch_mlp.down_proj.weight": "model-00010-of-00046.safetensors", + "model.layers.9.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00046.safetensors", + "model.layers.9.mlp.switch_mlp.up_proj.weight": "model-00009-of-00046.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00046.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00009-of-00046.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00046.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00046.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00009-of-00046.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00046.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00009-of-00046.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00046.safetensors", + "model.norm.weight": "model-00046-of-00046.safetensors" + } +} \ No newline at end of file diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..cef88e33d3754f456782ccbeafee2e549f2270e6 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,40 @@ +{ + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..8a090ee6b8bb2f47ede5c58e267ffd79dcdfcbe5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:840a2be2f18847f07571118fb785c9bde4726991852229d98469e421bf5d1064 +size 19971076 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..ec44d0e479c3067a4dd239a69cf6738e3d88c2be --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,341 @@ +{ + "added_tokens_decoder": { + "151329": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151330": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151331": { + "content": "[gMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151332": { + "content": "[sMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151333": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151334": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151335": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151336": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151337": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151338": { + "content": "<|observation|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151339": { + "content": "<|begin_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151340": { + "content": "<|end_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151341": { + "content": "<|begin_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151342": { + "content": "<|end_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151343": { + "content": "<|begin_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151344": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151345": { + "content": "<|begin_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151346": { + "content": "<|end_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151347": { + "content": "<|code_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151348": { + "content": "<|code_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151349": { + "content": "<|code_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151350": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151351": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151352": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151353": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151354": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151355": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151356": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151357": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151358": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151359": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151360": { + "content": "/nothink", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151361": { + "content": "<|begin_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151362": { + "content": "<|end_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151363": { + "content": "<|image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151364": { + "content": "<|video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151365": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151366": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|im_end|>", + "extra_special_tokens": {}, + "model_max_length": 128000, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "PreTrainedTokenizerFast" +}