commit e87d804a7fe02ca0fb6878452bb5bd7498df88fa Author: ModelHub XC Date: Sat May 2 12:25:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: TIGER-Lab/MAmmoTH-13B 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..7fd1645 --- /dev/null +++ b/README.md @@ -0,0 +1,101 @@ +--- +license: mit +datasets: +- TIGER-Lab/MathInstruct +language: +- en +--- +# 🦣 MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning + +Project Page: [https://tiger-ai-lab.github.io/MAmmoTH/](https://tiger-ai-lab.github.io/MAmmoTH/) + +Paper: [https://arxiv.org/pdf/2309.05653.pdf](https://arxiv.org/pdf/2309.05653.pdf) + +Code: [https://github.com/TIGER-AI-Lab/MAmmoTH](https://github.com/TIGER-AI-Lab/MAmmoTH) + + +## Introduction +We introduce 🦣 MAmmoTH, a series of open-source large language models (LLMs) specifically tailored for general math problem-solving. The MAmmoTH models are trained on 🤗 [MathInstruct Dataset](https://huggingface.co/datasets/TIGER-Lab/MathInstruct), a meticulously curated instruction tuning dataset that is lightweight yet generalizable. MathInstruct is compiled from 13 math rationale datasets, six of which are newly curated by this work. It uniquely focuses on the hybrid use of chain-of-thought (CoT) and program-of-thought (PoT) rationales, and ensures extensive coverage of diverse mathematical fields. + +| | **Base Model: Llama-2** | **Base Model: Code Llama** | +|-----|---------------------------------------------------------------|--------------------------------------------------------------------------| +| 7B | 🦣 [MAmmoTH-7B](https://huggingface.co/TIGER-Lab/MAmmoTH-7B) | 🦣 [MAmmoTH-Coder-7B](https://huggingface.co/TIGER-Lab/MAmmoTH-Coder-7B) | +| 13B | 🦣 [MAmmoTH-13B](https://huggingface.co/TIGER-Lab/MAmmoTH-13B) | 🦣 [MAmmoTH-Coder-13B](https://huggingface.co/TIGER-Lab/MAmmoTH-Coder-13B)| +| 34B | - | 🦣 [MAmmoTH-Coder-34B](https://huggingface.co/TIGER-Lab/MAmmoTH-Coder-34B)| +| 70B | 🦣 [MAmmoTH-70B](https://huggingface.co/TIGER-Lab/MAmmoTH-70B) | - | + + +## Training Data +The models are trained on the 🤗 [MathInstruct Dataset](https://huggingface.co/datasets/TIGER-Lab/MathInstruct), which is compiled from 13 different math rationale datasets. Check out the dataset card for more details. + + +## Training Procedure +The models are fine-tuned with the MathInstruct dataset using the original Llama-2 and Code Llama models as base models. The training procedure varies for different models based on their sizes. Check out our paper for more details. + +## Evaluation +The models are evaluated using open-ended and multiple-choice math problems from several datasets. Here are the results: + +| **Model** | **Decoding** | **GSM** | **MATH** | **AQuA** | **NumG** | **SVA** | **Mat** | **Sim** | **SAT** | **MMLU** | **AVG** | +|-----------------------|--------------|----------|----------|----------|----------|----------|----------|----------|----------|----------|----------| +| **MAmmoTH-7B** | CoT | 50.5 | 10.4 | 43.7 | 44.0 | 47.3 | 9.2 | 18.9 | 32.7 | 39.9 | 33.0 | +| | PoT | 51.6 | 28.7 | 43.3 | 52.3 | 65.1 | 41.9 | 48.2 | 39.1 | 44.6 | 46.1 | +| | **Hybrid** | **53.6** | **31.5** | **44.5** | **61.2** | **67.7** | **46.3** | **41.2** | **42.7** | **42.6** | **47.9** | +| **MAmmoTH-Coder-7B** | CoT | 22.4 | 7.9 | 36.2 | 36.0 | 37.0 | 8.2 | 7.2 | 32.7 | 34.6 | 24.7 | +| | PoT | 58.8 | 32.1 | 47.2 | 57.1 | 71.1 | 53.9 | 44.6 | 40.0 | 47.8 | 50.3 | +| | **Hybrid** | **59.4** | **33.4** | **47.2** | **66.4** | **71.4** | **55.4** | **45.9** | **40.5** | **48.3** | **52.0** | +| **MAmmoTH-13B** | CoT | 56.3 | 12.9 | 45.3 | 45.6 | 53.8 | 11.7 | 22.4 | 43.6 | 42.3 | 37.1 | +| | PoT | 61.3 | 32.6 | 48.8 | 59.6 | 72.2 | 48.5 | 40.3 | 46.8 | 45.4 | 50.6 | +| | **Hybrid** | **62.0** | **34.2** | **51.6** | **68.7** | **72.4** | **49.2** | **43.2** | **46.8** | **47.6** | **52.9** | +| **MAmmoTH-Coder-13B** | CoT | 32.1 | 10.2 | 40.6 | 36.2 | 43.0 | 9.6 | 10.1 | 40.9 | 36.6 | 28.8 | +| | PoT | 64.3 | 35.2 | 46.8 | 54.2 | 73.2 | 60.0 | 44.2 | 48.2 | 48.2 | 52.7 | +| | **Hybrid** | **64.7** | **36.3** | **46.9** | **66.8** | **73.7** | **61.5** | **47.1** | **48.6** | **48.3** | **54.9** | +| **MAmmoTH-Coder-33B** | CoT | 34.3 | 11.6 | 39.0 | 36.2 | 44.6 | 10.8 | 10.9 | 46.4 | 42.9 | 30.7 | +| | PoT | 72.3 | 42.8 | 53.8 | 59.6 | 84.0 | 64.7 | 50.6 | 58.6 | 52.7 | 59.9 | +| | **Hybrid** | **72.7** | **43.6** | **54.7** | **71.6** | **84.3** | **65.4** | **51.8** | **60.9** | **53.8** | **62.1** | +| **MAmmoTH-70B** | CoT | 72.4 | 21.1 | 57.9 | 58.9 | 71.6 | 20.0 | 31.9 | 57.3 | 52.1 | 49.2 | +| | PoT | 76.7 | 40.1 | 60.2 | 64.3 | 81.7 | 55.3 | 45.3 | 64.1 | 53.5 | 60.1 | +| | **Hybrid** | **76.9** | **41.8** | **65.0** | **74.4** | **82.4** | **55.6** | **51.4** | **66.4** | **56.7** | **63.4** | + +## Usage +You can use the models through Huggingface's Transformers library. Use the pipeline function to create a text-generation pipeline with the model of your choice, then feed in a math problem to get the solution. +Check our Github repo for more advanced use: [https://github.com/TIGER-AI-Lab/MAmmoTH](https://github.com/TIGER-AI-Lab/MAmmoTH) + +## Prompt Format +If you want to do CoT: +``` +Below is an instruction that describes a task. Write a response that appropriately completes the request. + +### Instruction: +{instruction} + +### Response: +``` + +If you want to do PoT: +``` +Below is an instruction that describes a task. Write a response that appropriately completes the request. + +### Instruction: +{instruction} Let's write a program. + +### Response: +``` + +## Intended Uses +These models are trained for research purposes. They are designed to solve general math problems. They can be used in educational software, tutoring systems, or any application where a solution to a math problem is needed. The models can generate both a chain of thought (CoT) rationale and a program of thought (PoT) rationale, providing a comprehensive solution to a given math problem. + +## Limitations +We've tried our best to build math generalist models. However, we acknowledge that the models' performance may vary based on the complexity and specifics of the math problem. Still not all mathematical fields can be covered comprehensively. + + +## Citation +If you use the models, data, or code from this project, please cite the original paper: + +``` +@article{yue2023mammoth, + title={MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning}, + author={Xiang Yue, Xingwei Qu, Ge Zhang, Yao Fu, Wenhao Huang, Huan Sun, Yu Su, Wenhu Chen}, + journal={arXiv preprint arXiv:2309.05653}, + year={2023} +} +``` \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..e41416d --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,3 @@ +{ + "[PAD]": 32000 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..c4d522f --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "_name_or_path": "/ML-A100/home/xiangyue/models/Llama-2-13b-hf", + "architectures": [ + "LlamaForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "num_key_value_heads": 40, + "pad_token_id": 0, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.29.1", + "use_cache": true, + "vocab_size": 32001 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..cc6257c --- /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": "4.29.1" +} diff --git a/pytorch_model-00001-of-00006.bin b/pytorch_model-00001-of-00006.bin new file mode 100644 index 0000000..de86dcc --- /dev/null +++ b/pytorch_model-00001-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74b5319f0991b558e8316e7b891ea634548f5b53bdf655c05a4dde47de855de8 +size 9956566923 diff --git a/pytorch_model-00002-of-00006.bin b/pytorch_model-00002-of-00006.bin new file mode 100644 index 0000000..060b3f2 --- /dev/null +++ b/pytorch_model-00002-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da20934d63d91d2f83294f716d875d7468ca6524a49ff74bbb86235abde6072b +size 9940859009 diff --git a/pytorch_model-00003-of-00006.bin b/pytorch_model-00003-of-00006.bin new file mode 100644 index 0000000..6652cf8 --- /dev/null +++ b/pytorch_model-00003-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:480130a352b28dc63cfd739eb31eedace9ad932ef043d2608f967d205320151b +size 9940859567 diff --git a/pytorch_model-00004-of-00006.bin b/pytorch_model-00004-of-00006.bin new file mode 100644 index 0000000..6bed8c6 --- /dev/null +++ b/pytorch_model-00004-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:715eebf63cc7e267fc12ef4f3e0fc6f34ea331aa28e5a0e569065055c581a796 +size 9867417913 diff --git a/pytorch_model-00005-of-00006.bin b/pytorch_model-00005-of-00006.bin new file mode 100644 index 0000000..95649e0 --- /dev/null +++ b/pytorch_model-00005-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5287dfd8be851682fc2055a3494111d199c7b161e7ca022c77d9db50962af0a9 +size 9867459649 diff --git a/pytorch_model-00006-of-00006.bin b/pytorch_model-00006-of-00006.bin new file mode 100644 index 0000000..c68ffac --- /dev/null +++ b/pytorch_model-00006-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40191a3ad0b48a0eb66cf5aee5f45d0f9ae56feb43c102af71b50aa46ebefb3e +size 2490497199 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..eb488e9 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,410 @@ +{ + "metadata": { + "total_size": 52063508480 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00006-of-00006.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin", + "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin", + "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.norm.weight": "pytorch_model-00006-of-00006.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..21edfc8 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": "[PAD]", + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "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..6a739a0 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,35 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "bos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "clean_up_tokenization_spaces": false, + "eos_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "legacy": false, + "model_max_length": 512, + "pad_token": null, + "padding_side": "right", + "sp_model_kwargs": {}, + "tokenizer_class": "LlamaTokenizer", + "unk_token": { + "__type": "AddedToken", + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +}