Upload folder using huggingface_hub
Browse files- README.md +119 -0
- added_tokens.json +3 -0
- config.json +27 -0
- generation_config.json +6 -0
- pytorch_model-00001-of-00007.bin +3 -0
- pytorch_model-00002-of-00007.bin +3 -0
- pytorch_model-00003-of-00007.bin +3 -0
- pytorch_model-00004-of-00007.bin +3 -0
- pytorch_model-00005-of-00007.bin +3 -0
- pytorch_model-00006-of-00007.bin +3 -0
- pytorch_model-00007-of-00007.bin +3 -0
- pytorch_model.bin.index.json +490 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +33 -0
README.md
ADDED
|
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama2
|
| 3 |
+
metrics:
|
| 4 |
+
- code_eval
|
| 5 |
+
library_name: transformers
|
| 6 |
+
tags:
|
| 7 |
+
- code
|
| 8 |
+
model-index:
|
| 9 |
+
- name: WizardCoder-Python-34B-V1.0
|
| 10 |
+
results:
|
| 11 |
+
- task:
|
| 12 |
+
type: text-generation
|
| 13 |
+
dataset:
|
| 14 |
+
type: openai_humaneval
|
| 15 |
+
name: HumanEval
|
| 16 |
+
metrics:
|
| 17 |
+
- name: pass@1
|
| 18 |
+
type: pass@1
|
| 19 |
+
value: 0.732
|
| 20 |
+
verified: false
|
| 21 |
+
---
|
| 22 |
+
|
| 23 |
+
## WizardCoder: Empowering Code Large Language Models with Evol-Instruct
|
| 24 |
+
|
| 25 |
+
<p style="font-size:28px;" align="center">
|
| 26 |
+
🏠 <a href="https://wizardlm.github.io/" target="_blank">Home Page</a> </p>
|
| 27 |
+
<p align="center">
|
| 28 |
+
<p align="center">
|
| 29 |
+
🤗 <a href="https://huggingface.co/WizardLM" target="_blank">HF Repo</a> •🐱 <a href="https://github.com/nlpxucan/WizardLM" target="_blank">Github Repo</a> • 🐦 <a href="https://twitter.com/WizardLM_AI" target="_blank">Twitter</a> </p>
|
| 30 |
+
<p align="center">
|
| 31 |
+
📃 <a href="https://arxiv.org/abs/2304.12244" target="_blank">[WizardLM]</a> • 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> • 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a> <br>
|
| 32 |
+
</p>
|
| 33 |
+
<p align="center">
|
| 34 |
+
👋 Join our <a href="https://discord.gg/VZjjHtWrKs" target="_blank">Discord</a>
|
| 35 |
+
</p>
|
| 36 |
+
|
| 37 |
+
## News
|
| 38 |
+
|
| 39 |
+
[2024/01/04] 🔥 We released **WizardCoder-33B-V1.1** trained from deepseek-coder-33b-base, the **SOTA OSS Code LLM** on [EvalPlus Leaderboard](https://evalplus.github.io/leaderboard.html), achieves **79.9 pass@1** on HumanEval, **73.2 pass@1** on HumanEval-Plus, **78.9 pass@1** on MBPP, and **66.9 pass@1** on MBPP-Plus.
|
| 40 |
+
|
| 41 |
+
[2024/01/04] 🔥 **WizardCoder-33B-V1.1** outperforms **ChatGPT 3.5**, **Gemini Pro**, and **DeepSeek-Coder-33B-instruct** on HumanEval and HumanEval-Plus pass@1.
|
| 42 |
+
|
| 43 |
+
[2024/01/04] 🔥 **WizardCoder-33B-V1.1** is comparable with **ChatGPT 3.5**, and surpasses **Gemini Pro** on MBPP and MBPP-Plus pass@1.
|
| 44 |
+
|
| 45 |
+
| Model | Checkpoint | Paper | HumanEval | HumanEval+ | MBPP | MBPP+ | License |
|
| 46 |
+
| ----- |------| ---- |------|-------| ----- | ----- |----- |
|
| 47 |
+
| GPT-4-Turbo (Nov 2023) | - | - | 85.4 | 81.7 | 83.0 | 70.7 |-|
|
| 48 |
+
| GPT-4 (May 2023) | - | - | 88.4 | 76.8 | - | - |-|
|
| 49 |
+
| GPT-3.5-Turbo (Nov 2023) | - | - | 72.6 | 65.9 | 81.7 | 69.4 |-|
|
| 50 |
+
| Gemini Pro | - | - | 63.4 | 55.5 | 72.9 | 57.9 |-|
|
| 51 |
+
| DeepSeek-Coder-33B-instruct | - | - | 78.7 | 72.6 | 78.7 | 66.7 |-|
|
| 52 |
+
| **WizardCoder-33B-V1.1** | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-33B-V1.1" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 79.9 | 73.2 | 78.9 | 66.9 | <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.1/resolve/main/LICENSE" target="_blank">MSFTResearch</a> |
|
| 53 |
+
| WizardCoder-Python-34B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-Python-34B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 73.2 | 64.6 | 73.2 | 59.9 | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
|
| 54 |
+
| WizardCoder-15B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-15B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 59.8 | 52.4 | -- | -- | <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a> |
|
| 55 |
+
| WizardCoder-Python-13B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-Python-13B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 64.0 | -- | -- | -- | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
|
| 56 |
+
| WizardCoder-Python-7B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-Python-7B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 55.5 | -- | -- | -- | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |
|
| 57 |
+
| WizardCoder-3B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-3B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 34.8 | -- | -- | -- | <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a> |
|
| 58 |
+
| WizardCoder-1B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-1B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 23.8 | -- | -- | -- | <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a> |
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
- Our **WizardMath-70B-V1.0** model slightly outperforms some closed-source LLMs on the GSM8K, including **ChatGPT 3.5**, **Claude Instant 1** and **PaLM 2 540B**.
|
| 63 |
+
- Our **WizardMath-70B-V1.0** model achieves **81.6 pass@1** on the [GSM8k Benchmarks](https://github.com/openai/grade-school-math), which is **24.8** points higher than the SOTA open-source LLM, and achieves **22.7 pass@1** on the [MATH Benchmarks](https://github.com/hendrycks/math), which is **9.2** points higher than the SOTA open-source LLM.
|
| 64 |
+
|
| 65 |
+
<font size=4>
|
| 66 |
+
|
| 67 |
+
| Model | Checkpoint | Paper | GSM8k | MATH |Online Demo| License|
|
| 68 |
+
| ----- |------| ---- |------|-------| ----- | ----- |
|
| 69 |
+
| WizardMath-70B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-70B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **81.6** | **22.7** |[Demo](http://47.103.63.15:50083/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a> |
|
| 70 |
+
| WizardMath-13B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-13B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **63.9** | **14.0** |[Demo](http://47.103.63.15:50082/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a> |
|
| 71 |
+
| WizardMath-7B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **54.9** | **10.7** | [Demo ](http://47.103.63.15:50080/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a>|
|
| 72 |
+
</font>
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
- [08/09/2023] We released **WizardLM-70B-V1.0** model. Here is [Full Model Weight](https://huggingface.co/WizardLM/WizardLM-70B-V1.0).
|
| 76 |
+
|
| 77 |
+
<font size=4>
|
| 78 |
+
|
| 79 |
+
|
| 80 |
+
| <sup>Model</sup> | <sup>Checkpoint</sup> | <sup>Paper</sup> |<sup>MT-Bench</sup> | <sup>AlpacaEval</sup> | <sup>GSM8k</sup> | <sup>HumanEval</sup> | <sup>License</sup>|
|
| 81 |
+
| ----- |------| ---- |------|-------| ----- | ----- | ----- |
|
| 82 |
+
| <sup>**WizardLM-70B-V1.0**</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-70B-V1.0" target="_blank">HF Link</a> </sup>|<sup>📃**Coming Soon**</sup>| <sup>**7.78**</sup> | <sup>**92.91%**</sup> |<sup>**77.6%**</sup> | <sup> **50.6**</sup>|<sup> <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License </a></sup> |
|
| 83 |
+
| <sup>WizardLM-13B-V1.2</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.2" target="_blank">HF Link</a> </sup>| | <sup>7.06</sup> | <sup>89.17%</sup> |<sup>55.3%</sup> | <sup>36.6 </sup>|<sup> <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License </a></sup> |
|
| 84 |
+
| <sup>WizardLM-13B-V1.1</sup> |<sup> 🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.1" target="_blank">HF Link</a> </sup> | | <sup>6.76</sup> |<sup>86.32%</sup> | | <sup>25.0 </sup>| <sup>Non-commercial</sup>|
|
| 85 |
+
| <sup>WizardLM-30B-V1.0</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-30B-V1.0" target="_blank">HF Link</a></sup> | | <sup>7.01</sup> | | | <sup>37.8 </sup>| <sup>Non-commercial</sup> |
|
| 86 |
+
| <sup>WizardLM-13B-V1.0</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.0" target="_blank">HF Link</a> </sup> | | <sup>6.35</sup> | <sup>75.31%</sup> | | <sup> 24.0 </sup> | <sup>Non-commercial</sup>|
|
| 87 |
+
| <sup>WizardLM-7B-V1.0 </sup>| <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-7B-V1.0" target="_blank">HF Link</a> </sup> |<sup> 📃 <a href="https://arxiv.org/abs/2304.12244" target="_blank">[WizardLM]</a> </sup>| | | |<sup>19.1 </sup>|<sup> Non-commercial</sup>|
|
| 88 |
+
</font>
|
| 89 |
+
|
| 90 |
+
|
| 91 |
+
## Comparing WizardCoder-Python-34B-V1.0 with Other LLMs.
|
| 92 |
+
|
| 93 |
+
🔥 The following figure shows that our **WizardCoder-Python-34B-V1.0 attains the second position in this benchmark**, surpassing GPT4 (2023/03/15, 73.2 vs. 67.0), ChatGPT-3.5 (73.2 vs. 72.5) and Claude2 (73.2 vs. 71.2).
|
| 94 |
+
|
| 95 |
+
<p align="center" width="100%">
|
| 96 |
+
<a ><img src="https://raw.githubusercontent.com/nlpxucan/WizardLM/main/WizardCoder/imgs/compare_sota.png" alt="WizardCoder" style="width: 96%; min-width: 300px; display: block; margin: auto;"></a>
|
| 97 |
+
</p>
|
| 98 |
+
|
| 99 |
+
## Prompt Format
|
| 100 |
+
```
|
| 101 |
+
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"
|
| 102 |
+
```
|
| 103 |
+
|
| 104 |
+
## Inference Demo Script
|
| 105 |
+
|
| 106 |
+
We provide the inference demo code [here](https://github.com/nlpxucan/WizardLM/tree/main/demo).
|
| 107 |
+
|
| 108 |
+
## Citation
|
| 109 |
+
|
| 110 |
+
Please cite the repo if you use the data, method or code in this repo.
|
| 111 |
+
|
| 112 |
+
```
|
| 113 |
+
@article{luo2023wizardcoder,
|
| 114 |
+
title={WizardCoder: Empowering Code Large Language Models with Evol-Instruct},
|
| 115 |
+
author={Luo, Ziyang and Xu, Can and Zhao, Pu and Sun, Qingfeng and Geng, Xiubo and Hu, Wenxiang and Tao, Chongyang and Ma, Jing and Lin, Qingwei and Jiang, Daxin},
|
| 116 |
+
journal={arXiv preprint arXiv:2306.08568},
|
| 117 |
+
year={2023}
|
| 118 |
+
}
|
| 119 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "codellama/CodeLlama-34b-Python-hf",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LlamaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 8192,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 22016,
|
| 12 |
+
"max_position_embeddings": 16384,
|
| 13 |
+
"model_type": "llama",
|
| 14 |
+
"num_attention_heads": 64,
|
| 15 |
+
"num_hidden_layers": 48,
|
| 16 |
+
"num_key_value_heads": 8,
|
| 17 |
+
"pad_token_id": 0,
|
| 18 |
+
"pretraining_tp": 1,
|
| 19 |
+
"rms_norm_eps": 1e-05,
|
| 20 |
+
"rope_scaling": null,
|
| 21 |
+
"rope_theta": 1000000,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "float16",
|
| 24 |
+
"transformers_version": "4.31.0",
|
| 25 |
+
"use_cache": false,
|
| 26 |
+
"vocab_size": 32001
|
| 27 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.31.0"
|
| 6 |
+
}
|
pytorch_model-00001-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c52afae51f496879ae2164f12c4f9b879cb9ee80bd32a7a4a485b3994e88720
|
| 3 |
+
size 9852657179
|
pytorch_model-00002-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3a02a24ccd66d22f40d9b1325ee5b60397d7f467d1083300f5d9c5243556833
|
| 3 |
+
size 9689096447
|
pytorch_model-00003-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55685a1c1a2577945caa13e6dcab8d36f8213dd35e6960a19574c016e8cce0d3
|
| 3 |
+
size 9689096447
|
pytorch_model-00004-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e0d6753679e560bc1bfce102c935886ec9bd3c44244629a23338a2f6cab5897
|
| 3 |
+
size 9689096447
|
pytorch_model-00005-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56afdc78f10f1999b4b85a34af13bef0918e69416c1e2e8ce81ca2436f7cb4d2
|
| 3 |
+
size 9689096447
|
pytorch_model-00006-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57ae73dec1cf6cc8b16248f36848965ba583e10682cd787e29921337a4b3d805
|
| 3 |
+
size 9689096447
|
pytorch_model-00007-of-00007.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7d8fb909acd6d0cb42a2fd9e0a688fdc5a9db7755dd44a52857b80418c669b3
|
| 3 |
+
size 9190005097
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,490 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 67487979520
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00007-of-00007.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 16 |
+
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 26 |
+
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
| 27 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 28 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 29 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 30 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 31 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 32 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 33 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 34 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 35 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 36 |
+
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
| 37 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 38 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 39 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 40 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 41 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 42 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 43 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 44 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 45 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 46 |
+
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
| 47 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 48 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 49 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 50 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 51 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 52 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 53 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 54 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 55 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 56 |
+
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
| 57 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 58 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 59 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 60 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 61 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 62 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 63 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 64 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 65 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 66 |
+
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
| 67 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 68 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 69 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 70 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 71 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 72 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 73 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 74 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 75 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 76 |
+
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
| 77 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 78 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 79 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 80 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 81 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 82 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 83 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 84 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 85 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 86 |
+
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
| 87 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 88 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 89 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 90 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 91 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 92 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 93 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 94 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 95 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 96 |
+
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
| 97 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 98 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 99 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 100 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 101 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 102 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 103 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 104 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 105 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 106 |
+
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
| 107 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 108 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 109 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 110 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 111 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 112 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 113 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 114 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 115 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 116 |
+
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
| 117 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 118 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 119 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 120 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 121 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 122 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
| 123 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 124 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 125 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 126 |
+
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
| 127 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 128 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
| 129 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 130 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 131 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 132 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
| 133 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 134 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 135 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 136 |
+
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
| 137 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 138 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 139 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 140 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 141 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 142 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 143 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 144 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 145 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 146 |
+
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
| 147 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
| 148 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 149 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 150 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 151 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 152 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 153 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 154 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 155 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 156 |
+
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
| 157 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 158 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 159 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 160 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 161 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 162 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 163 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 164 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 165 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 166 |
+
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
| 167 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 168 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 169 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 170 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 171 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 172 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 173 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 174 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 175 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 176 |
+
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
| 177 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 178 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 179 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 180 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 181 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 182 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 183 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 184 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 185 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 186 |
+
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
| 187 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 188 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 189 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 190 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 191 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 192 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 193 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 194 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 195 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 196 |
+
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
| 197 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 198 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 199 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 200 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 201 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 202 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
| 203 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 204 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 205 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 206 |
+
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
| 207 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 208 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 209 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 210 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 211 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 212 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 213 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 214 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 215 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 216 |
+
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
| 217 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
| 218 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 219 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 220 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 221 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 222 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 223 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 224 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 225 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 226 |
+
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
| 227 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 228 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 229 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 230 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 231 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 232 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 233 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 234 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 235 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 236 |
+
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
| 237 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 238 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
| 239 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 240 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 241 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 242 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
| 243 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 244 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 245 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 246 |
+
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
| 247 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 248 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 249 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 250 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 251 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 252 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 253 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 254 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 255 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 256 |
+
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
| 257 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 258 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 259 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 260 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 261 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 262 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 263 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 264 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 265 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 266 |
+
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
| 267 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 268 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 269 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 270 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 271 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 272 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 273 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 274 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 275 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 276 |
+
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
| 277 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 278 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 279 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 280 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 281 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 282 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
| 283 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 284 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 285 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 286 |
+
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
| 287 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 288 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 289 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 290 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 291 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 292 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 293 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 294 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 295 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 296 |
+
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
| 297 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
| 298 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 299 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 300 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 301 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 302 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 303 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 304 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 305 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 306 |
+
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
| 307 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 308 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 309 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 310 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 311 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 312 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 313 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 314 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 315 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 316 |
+
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
| 317 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 318 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 319 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 320 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 321 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 322 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 323 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 324 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 325 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 326 |
+
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
| 327 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 328 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 329 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 330 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 331 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 332 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 333 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 334 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 335 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 336 |
+
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
| 337 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 338 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 339 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 340 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 341 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 342 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 343 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 344 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 345 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 346 |
+
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
| 347 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 348 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
| 349 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 350 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 351 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 352 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
| 353 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 354 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 355 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 356 |
+
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
| 357 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 358 |
+
"model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 359 |
+
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 360 |
+
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 361 |
+
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 362 |
+
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
| 363 |
+
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 364 |
+
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 365 |
+
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 366 |
+
"model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
| 367 |
+
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 368 |
+
"model.layers.41.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 369 |
+
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 370 |
+
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 371 |
+
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 372 |
+
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 373 |
+
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 374 |
+
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 375 |
+
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 376 |
+
"model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
| 377 |
+
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
| 378 |
+
"model.layers.42.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 379 |
+
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 380 |
+
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 381 |
+
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 382 |
+
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 383 |
+
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 384 |
+
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 385 |
+
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 386 |
+
"model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
| 387 |
+
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 388 |
+
"model.layers.43.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 389 |
+
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 390 |
+
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 391 |
+
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 392 |
+
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 393 |
+
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 394 |
+
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 395 |
+
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 396 |
+
"model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
| 397 |
+
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 398 |
+
"model.layers.44.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 399 |
+
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 400 |
+
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 401 |
+
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 402 |
+
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 403 |
+
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 404 |
+
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 405 |
+
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 406 |
+
"model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
| 407 |
+
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 408 |
+
"model.layers.45.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 409 |
+
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 410 |
+
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 411 |
+
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 412 |
+
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 413 |
+
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 414 |
+
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 415 |
+
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 416 |
+
"model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
| 417 |
+
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 418 |
+
"model.layers.46.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 419 |
+
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 420 |
+
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 421 |
+
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 422 |
+
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 423 |
+
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 424 |
+
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 425 |
+
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 426 |
+
"model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
| 427 |
+
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 428 |
+
"model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 429 |
+
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 430 |
+
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 431 |
+
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 432 |
+
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
| 433 |
+
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 434 |
+
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 435 |
+
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 436 |
+
"model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
| 437 |
+
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
| 438 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
| 439 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 440 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 441 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 442 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
| 443 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 444 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 445 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 446 |
+
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
| 447 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 448 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 449 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 450 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 451 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 452 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 453 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 454 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 455 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 456 |
+
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
| 457 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
| 458 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 459 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 460 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 461 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 462 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 463 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 464 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 465 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 466 |
+
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
| 467 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 468 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 469 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 470 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 471 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 472 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 473 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 474 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 475 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 476 |
+
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
| 477 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 478 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 479 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 480 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 481 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 482 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
| 483 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 484 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 485 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 486 |
+
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
| 487 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
| 488 |
+
"model.norm.weight": "pytorch_model-00007-of-00007.bin"
|
| 489 |
+
}
|
| 490 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "</s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"unk_token": "</s>"
|
| 6 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"__type": "AddedToken",
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"clean_up_tokenization_spaces": false,
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"legacy": null,
|
| 20 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
+
"pad_token": null,
|
| 22 |
+
"padding_side": "right",
|
| 23 |
+
"sp_model_kwargs": {},
|
| 24 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": true,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
}
|
| 33 |
+
}
|