commit 06002322f3129270f6c2638f2481aeaf3c98979d Author: ModelHub XC Date: Tue Apr 21 20:11:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: lmsys/vicuna-33b-v1.3 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..063ad25 --- /dev/null +++ b/README.md @@ -0,0 +1,44 @@ +--- +inference: false +--- + +# Vicuna Model Card + +## Model Details + +Vicuna is a chat assistant trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. + +- **Developed by:** [LMSYS](https://lmsys.org/) +- **Model type:** An auto-regressive language model based on the transformer architecture. +- **License:** Non-commercial license +- **Finetuned from model:** [LLaMA](https://arxiv.org/abs/2302.13971). + +### Model Sources + +- **Repository:** https://github.com/lm-sys/FastChat +- **Blog:** https://lmsys.org/blog/2023-03-30-vicuna/ +- **Paper:** https://arxiv.org/abs/2306.05685 +- **Demo:** https://chat.lmsys.org/ + +## Uses + +The primary use of Vicuna is research on large language models and chatbots. +The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence. + +## How to Get Started with the Model + +- Command line interface: https://github.com/lm-sys/FastChat#vicuna-weights. +- APIs (OpenAI API, Huggingface API): https://github.com/lm-sys/FastChat/tree/main#api. + +## Training Details + +Vicuna v1.3 is fine-tuned from LLaMA with supervised instruction fine-tuning. +The training data is around 125K conversations collected from ShareGPT.com. +See more details in the "Training Details of Vicuna Models" section in the appendix of this [paper](https://arxiv.org/pdf/2306.05685.pdf). + +## Evaluation + +Vicuna is evaluated with standard benchmarks, human preference, and LLM-as-a-judge. See more details in this [paper](https://arxiv.org/pdf/2306.05685.pdf) and [leaderboard](https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboard). + +## Difference between different versions of Vicuna +See [vicuna_weights_version.md](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..930d8e5 --- /dev/null +++ b/config.json @@ -0,0 +1,23 @@ +{ + "_name_or_path": "/home/ubuntu/model_weights/vicuna-33b-v1.3", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 6656, + "initializer_range": 0.02, + "intermediate_size": 17920, + "max_position_embeddings": 2048, + "model_type": "llama", + "num_attention_heads": 52, + "num_hidden_layers": 60, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "tie_word_embeddings": false, + "torch_dtype": "float16", + "transformers_version": "4.28.1", + "use_cache": true, + "vocab_size": 32000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..1372199 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "pad_token_id": 0, + "transformers_version": "4.28.1" +} diff --git a/pytorch_model-00001-of-00007.bin b/pytorch_model-00001-of-00007.bin new file mode 100644 index 0000000..4575236 --- /dev/null +++ b/pytorch_model-00001-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dde176666dbac70c86826fc33aafc83757589ce4d601699c1cbe19b3992f467d +size 9818324627 diff --git a/pytorch_model-00002-of-00007.bin b/pytorch_model-00002-of-00007.bin new file mode 100644 index 0000000..0a88ab1 --- /dev/null +++ b/pytorch_model-00002-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d8a9482098194e48b67bd26c5af0bf4af4ce2e4aea3e4afbe4d41585f3eba7 +size 9958102743 diff --git a/pytorch_model-00003-of-00007.bin b/pytorch_model-00003-of-00007.bin new file mode 100644 index 0000000..a6fa1a0 --- /dev/null +++ b/pytorch_model-00003-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14f40574376c5475e0b6af703fb4d9b0a8addcd63a2805c3069bb2ef8dcda583 +size 9896734715 diff --git a/pytorch_model-00004-of-00007.bin b/pytorch_model-00004-of-00007.bin new file mode 100644 index 0000000..bfe288a --- /dev/null +++ b/pytorch_model-00004-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445c09eaaef05a199f775733a0a66a50da5dae1f68b8f484178cbd8aed5f5b67 +size 9869470481 diff --git a/pytorch_model-00005-of-00007.bin b/pytorch_model-00005-of-00007.bin new file mode 100644 index 0000000..5afc593 --- /dev/null +++ b/pytorch_model-00005-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e9efc61a84386c71a53128be066c6c8eaf5ecd0346b787656a81fcec6d1491d +size 9869470445 diff --git a/pytorch_model-00006-of-00007.bin b/pytorch_model-00006-of-00007.bin new file mode 100644 index 0000000..ac6a58f --- /dev/null +++ b/pytorch_model-00006-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1751cd8ea5c34a4ecf92602c90952b768a25c71a193abfc7e91d6d694a0900b +size 9958102743 diff --git a/pytorch_model-00007-of-00007.bin b/pytorch_model-00007-of-00007.bin new file mode 100644 index 0000000..89a93dd --- /dev/null +++ b/pytorch_model-00007-of-00007.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83b05caa9d26bcf406a1108b7e314e14edfab2cf9d3d4a21e2dac782d53a60ae +size 5687903281 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..c76e80d --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,610 @@ +{ + "metadata": { + "total_size": 65057902592 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00007-of-00007.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.40.input_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.40.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.40.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.41.input_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.41.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.41.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.42.input_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.42.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.42.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.43.input_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.43.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.43.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.44.input_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.44.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.44.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.45.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.45.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.45.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin", + "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin", + "model.layers.46.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.46.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.46.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.47.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.47.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.47.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.48.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.48.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.48.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.49.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.49.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.49.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.50.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.50.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.50.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.51.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.51.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.51.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.52.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.52.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.52.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.53.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.53.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.53.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.54.input_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.54.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.54.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin", + "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.55.input_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.55.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.55.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin", + "model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin", + "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.56.input_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.56.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.56.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin", + "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.57.input_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.57.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.57.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin", + "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.58.input_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.58.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.58.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin", + "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.59.input_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.59.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.59.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin", + "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin", + "model.norm.weight": "pytorch_model-00007-of-00007.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..f928b24 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} 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..5ab645d --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,34 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "model_max_length": 2048, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +}