commit 6202a4daec6d854c459d171fb833fb4835fd94e0 Author: ModelHub XC Date: Tue Apr 21 17:55:50 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bofenghuang/vigogne-2-70b-chat Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..88be4a5 --- /dev/null +++ b/README.md @@ -0,0 +1,144 @@ +--- +license: llama2 +language: fr +pipeline_tag: text-generation +inference: false +tags: +- LLM +- llama-2 +- finetuned +--- + +

+Vigogne +

+ +# Vigogne-2-70B-Chat: A Llama-2-based French Chat LLM + +Vigogne-2-70B-Chat is a French chat LLM, based on [Llama-2-70B](https://ai.meta.com/llama), optimized to generate helpful and coherent responses in conversations with users. + +Check out our [release blog](https://github.com/bofenghuang/vigogne/blob/main/blogs/2023-08-17-vigogne-chat-v2_0.md) and [GitHub repository](https://github.com/bofenghuang/vigogne) for more information. + +**Usage and License Notices**: Vigogne-2-70B-Chat follows Llama-2's [usage policy](https://ai.meta.com/llama/use-policy). A significant portion of the training data is distilled from GPT-3.5-Turbo and GPT-4, kindly use it cautiously to avoid any violations of OpenAI's [terms of use](https://openai.com/policies/terms-of-use). + +## Prompt Template + +We used a prompt template adapted from the chat format of Llama-2. + +You can apply this formatting using the [chat template](https://huggingface.co/docs/transformers/main/chat_templating) through the `apply_chat_template()` method. + +```python +from transformers import AutoTokenizer + +tokenizer = AutoTokenizer.from_pretrained("bofenghuang/vigogne-2-70b-chat") + +conversation = [ + {"role": "user", "content": "Bonjour ! Comment ça va aujourd'hui ?"}, + {"role": "assistant", "content": "Bonjour ! Je suis une IA, donc je n'ai pas de sentiments, mais je suis prêt à vous aider. Comment puis-je vous assister aujourd'hui ?"}, + {"role": "user", "content": "Quelle est la hauteur de la Tour Eiffel ?"}, + {"role": "assistant", "content": "La Tour Eiffel mesure environ 330 mètres de hauteur."}, + {"role": "user", "content": "Comment monter en haut ?"}, +] + +print(tokenizer.apply_chat_template(conversation, tokenize=False, add_generation_prompt=True)) +``` + +You will get + +``` +[INST] <> +Vous êtes Vigogne, un assistant IA créé par Zaion Lab. Vous suivez extrêmement bien les instructions. Aidez autant que vous le pouvez. +<> + +Bonjour ! Comment ça va aujourd'hui ? [/INST] Bonjour ! Je suis une IA, donc je n'ai pas de sentiments, mais je suis prêt à vous aider. Comment puis-je vous assister aujourd'hui ? [INST] Quelle est la hauteur de la Tour Eiffel ? [/INST] La Tour Eiffel mesure environ 330 mètres de hauteur. [INST] Comment monter en haut ? [/INST] +``` + +## Usage + + + +### Inference using the unquantized model with 🤗 Transformers + +```python +from typing import Dict, List, Optional +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig, TextStreamer + +model_name_or_path = "bofenghuang/vigogne-2-70b-chat" +tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, padding_side="right", use_fast=False) +model = AutoModelForCausalLM.from_pretrained(model_name_or_path, torch_dtype=torch.float16, device_map="auto") + +streamer = TextStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True) + + +def chat( + query: str, + history: Optional[List[Dict]] = None, + temperature: float = 0.7, + top_p: float = 1.0, + top_k: float = 0, + repetition_penalty: float = 1.1, + max_new_tokens: int = 1024, + **kwargs, +): + if history is None: + history = [] + + history.append({"role": "user", "content": query}) + + input_ids = tokenizer.apply_chat_template(history, return_tensors="pt").to(model.device) + input_length = input_ids.shape[1] + + generated_outputs = model.generate( + input_ids=input_ids, + generation_config=GenerationConfig( + temperature=temperature, + do_sample=temperature > 0.0, + top_p=top_p, + top_k=top_k, + repetition_penalty=repetition_penalty, + max_new_tokens=max_new_tokens, + pad_token_id=tokenizer.eos_token_id, + **kwargs, + ), + streamer=streamer, + return_dict_in_generate=True, + ) + + generated_tokens = generated_outputs.sequences[0, input_length:] + generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True) + + history.append({"role": "assistant", "content": generated_text}) + + return generated_text, history + + +# 1st round +response, history = chat("Un escargot parcourt 100 mètres en 5 heures. Quelle est sa vitesse ?", history=None) + +# 2nd round +response, history = chat("Quand il peut dépasser le lapin ?", history=history) + +# 3rd round +response, history = chat("Écris une histoire imaginative qui met en scène une compétition de course entre un escargot et un lapin.", history=history) +``` + +You can also use the Google Colab Notebook provided below. + +Open In Colab + +## Limitations + +Vigogne is still under development, and there are many limitations that have to be addressed. Please note that it is possible that the model generates harmful or biased content, incorrect information or generally unhelpful answers. + +## Acknowledgements + +The model training was conducted on the [Jean-Zay supercomputer](http://www.idris.fr/eng/jean-zay/jean-zay-presentation-eng.html) at GENCI, and we extend our gratitude to the IDRIS team for their responsive support throughout the project. diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..cbce74e --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,5 @@ +{ + "": 2, + "": 1, + "": 0 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..510ee75 --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "_name_or_path": "meta-llama/Llama-2-70b-hf", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 80, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.35.0.dev0", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..2233c25 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "bos_token_id": 1, + "do_sample": true, + "eos_token_id": 2, + "max_length": 4096, + "pad_token_id": 0, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.35.0.dev0" +} diff --git a/logo_v2.jpg b/logo_v2.jpg new file mode 100644 index 0000000..dfcc7ed Binary files /dev/null and b/logo_v2.jpg differ diff --git a/pytorch_model-00001-of-00015.bin b/pytorch_model-00001-of-00015.bin new file mode 100644 index 0000000..b5478ec --- /dev/null +++ b/pytorch_model-00001-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68383a84d769ad2cd86da118e3c8831bf2edeee6799013eb8be3efdc88b630d7 +size 9852601317 diff --git a/pytorch_model-00002-of-00015.bin b/pytorch_model-00002-of-00015.bin new file mode 100644 index 0000000..4275b8c --- /dev/null +++ b/pytorch_model-00002-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228467e8525ca2d07d5e9a90f0b1d2584718229f2873848c9765f65e4c9b50c8 +size 9798108893 diff --git a/pytorch_model-00003-of-00015.bin b/pytorch_model-00003-of-00015.bin new file mode 100644 index 0000000..5687a8f --- /dev/null +++ b/pytorch_model-00003-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ca710b3a78b911ac63b76fe72e6bbe575f8ff32119205588f41d44b8ebd9021 +size 9965880015 diff --git a/pytorch_model-00004-of-00015.bin b/pytorch_model-00004-of-00015.bin new file mode 100644 index 0000000..4882b64 --- /dev/null +++ b/pytorch_model-00004-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad0bb143f5170effdcf1a4bd813ff15828b774b4c1fab2f68b7db569fa0eeddf +size 9798075365 diff --git a/pytorch_model-00005-of-00015.bin b/pytorch_model-00005-of-00015.bin new file mode 100644 index 0000000..bd484d8 --- /dev/null +++ b/pytorch_model-00005-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe39a2fadc65a87b0d90a9a585444284f315aee5b622967ce76d31c77cb96bc8 +size 9798108809 diff --git a/pytorch_model-00006-of-00015.bin b/pytorch_model-00006-of-00015.bin new file mode 100644 index 0000000..5bc1870 --- /dev/null +++ b/pytorch_model-00006-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4b61498a0a7ba56211e19454efeac21b9f86411a579411ba46c34c61ac19a81 +size 9798108893 diff --git a/pytorch_model-00007-of-00015.bin b/pytorch_model-00007-of-00015.bin new file mode 100644 index 0000000..933de30 --- /dev/null +++ b/pytorch_model-00007-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2154a0eff3c1791664957b5cb56cccb8e858e105e38270c305f76b6862ef0626 +size 9965880015 diff --git a/pytorch_model-00008-of-00015.bin b/pytorch_model-00008-of-00015.bin new file mode 100644 index 0000000..6b07da2 --- /dev/null +++ b/pytorch_model-00008-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a06019e9ccb02e7b2ec5f50b0898ed6093a658f8f98855e0bfbab9520d1e5977 +size 9798075365 diff --git a/pytorch_model-00009-of-00015.bin b/pytorch_model-00009-of-00015.bin new file mode 100644 index 0000000..883b813 --- /dev/null +++ b/pytorch_model-00009-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13e5209d2c17ed1ea61beaea7cf05f4a92a6c16d8528e89b87ba8d97932b52e4 +size 9798108809 diff --git a/pytorch_model-00010-of-00015.bin b/pytorch_model-00010-of-00015.bin new file mode 100644 index 0000000..a686b95 --- /dev/null +++ b/pytorch_model-00010-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae42f3274d1394b2a036dd5f670a6a0c82e856b00845a3342d3f7fcc5dc93775 +size 9798108893 diff --git a/pytorch_model-00011-of-00015.bin b/pytorch_model-00011-of-00015.bin new file mode 100644 index 0000000..e2107b8 --- /dev/null +++ b/pytorch_model-00011-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d205eca05e6ec71c5e9131e9b0a377b56ba762ce6b63a252165907e7448a13c9 +size 9965880015 diff --git a/pytorch_model-00012-of-00015.bin b/pytorch_model-00012-of-00015.bin new file mode 100644 index 0000000..5efe66a --- /dev/null +++ b/pytorch_model-00012-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08def4fc98ab6d9fac426fd4523c1e58e99febf034f5885f3c8a1a68324d278e +size 9798075365 diff --git a/pytorch_model-00013-of-00015.bin b/pytorch_model-00013-of-00015.bin new file mode 100644 index 0000000..eb5cd06 --- /dev/null +++ b/pytorch_model-00013-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e5aa308e17005d330d6ab3a10e992a73b628321a69381a9e2b45439444113f4 +size 9798108809 diff --git a/pytorch_model-00014-of-00015.bin b/pytorch_model-00014-of-00015.bin new file mode 100644 index 0000000..89f91de --- /dev/null +++ b/pytorch_model-00014-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9b3834b5d771d586331b548dce27b02e2e05bb2a3be995ef82a373b76002819 +size 9496134339 diff --git a/pytorch_model-00015-of-00015.bin b/pytorch_model-00015-of-00015.bin new file mode 100644 index 0000000..3d8520b --- /dev/null +++ b/pytorch_model-00015-of-00015.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28bf066580fc9703db71bed526e19e30e641cdf81f9ddaafe73e694541f29cff +size 524288938 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..5e7e7a0 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,730 @@ +{ + "metadata": { + "total_size": 137953296384 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00015-of-00015.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.40.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.40.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.41.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.41.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.42.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.43.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.44.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.45.input_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.45.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.45.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin", + "model.layers.46.input_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.46.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.46.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.47.input_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.47.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.47.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.48.input_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.48.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.48.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.49.input_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.49.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.49.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin", + "model.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.50.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.50.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.51.input_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.51.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.51.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin", + "model.layers.52.input_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.52.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.52.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.53.input_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.53.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.53.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.54.input_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.54.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.54.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.55.input_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.55.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.55.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.56.input_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.56.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.56.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.57.input_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.57.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.57.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin", + "model.layers.58.input_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.58.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.58.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.59.input_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.59.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.59.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.60.input_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.60.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.60.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.61.input_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.61.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.61.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.62.input_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.62.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.62.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin", + "model.layers.63.input_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.63.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.63.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.64.input_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.64.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.64.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.64.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.64.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.65.input_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.65.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.65.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.65.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.65.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.66.input_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.66.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.66.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.66.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.66.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.67.input_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.67.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.67.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.67.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.67.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.68.input_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.68.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.68.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.68.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.68.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin", + "model.layers.69.input_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.69.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.69.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.69.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.69.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.70.input_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.70.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.70.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.70.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.70.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.71.input_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.71.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.71.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.71.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.71.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.72.input_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.72.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.72.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.72.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.72.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.73.input_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.73.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.73.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.73.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.73.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.74.input_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.74.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.74.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.74.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.74.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin", + "model.layers.75.input_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.75.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.75.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.75.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.75.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.76.input_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.76.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.76.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.76.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.76.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.77.input_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.77.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.77.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.77.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.77.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.78.input_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.78.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.78.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.78.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.78.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.79.input_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.79.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.79.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.79.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.79.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin", + "model.norm.weight": "pytorch_model-00014-of-00015.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..a52c50a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,5 @@ +{ + "bos_token": "", + "eos_token": "", + "unk_token": "" +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..6c00c74 --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 +size 499723 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..3a419f6 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,45 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif true == true and not '<>' in messages[0]['content'] %}{% set loop_messages = messages %}{% set system_message = 'Vous êtes Vigogne, un assistant IA créé par Zaion Lab. Vous suivez extrêmement bien les instructions. Aidez autant que vous le pouvez.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<>\\n' + system_message + '\\n<>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<>\\n' + content.strip() + '\\n<>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": false, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "tokenizer_file": null, + "unk_token": "", + "use_default_system_prompt": true +}