6d25d761fb75df5c472aa728c368e0d0d239719073d451d9a2b7cda3234abe54
Browse files- README.md +137 -0
- config.json +26 -0
- generation_config.json +6 -0
- pytorch_model-00025-of-00025.bin +3 -0
- pytorch_model.bin.index.json +442 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +37 -0
README.md
ADDED
|
@@ -0,0 +1,137 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: gpl-3.0
|
| 3 |
+
language:
|
| 4 |
+
- zh
|
| 5 |
+
- en
|
| 6 |
+
library_name: transformers
|
| 7 |
+
pipeline_tag: text-generation
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# Ziya-Coding-34B-v1.0
|
| 11 |
+
|
| 12 |
+
|
| 13 |
+
# 姜子牙系列模型
|
| 14 |
+
|
| 15 |
+
- [Ziya-LLaMA-13B-v1.1](https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-v1.1)
|
| 16 |
+
- [Ziya-LLaMA-13B-v1](https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-v1)
|
| 17 |
+
- [Ziya-LLaMA-7B-Reward](https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-7B-Reward)
|
| 18 |
+
- [Ziya-LLaMA-13B-Pretrain-v1](https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-Pretrain-v1)
|
| 19 |
+
- [Ziya-BLIP2-14B-Visual-v1](https://huggingface.co/IDEA-CCNL/Ziya-BLIP2-14B-Visual-v1)
|
| 20 |
+
- [Ziya-Writing-LLaMa-13B-v1](https://huggingface.co/IDEA-CCNL/Ziya-Writing-LLaMa-13B-v1)
|
| 21 |
+
- [Ziya-Coding-15B-v1](https://huggingface.co/IDEA-CCNL/Ziya-Coding-15B-v1)
|
| 22 |
+
|
| 23 |
+
## 简介 Brief Introduction
|
| 24 |
+
|
| 25 |
+
使用自然语言生成高质量的代码是大模型落地中的高频需求。今天，IDEA研究院封神榜团队正式开源最新的代码大模型Ziya-Coding-34B-v1.0，我们在HumanEval Pass@1的评测上，取得了75.5的好成绩，超过了GPT-4（67.0）的得分，也成为目前已知开源模型新高。封神榜团队正在为社区提供先进的大模型技术和经验，帮助生产和定制更多优秀垂类模型，推进大模型生态发展。
|
| 26 |
+
|
| 27 |
+
|
| 28 |
+
Generating high-quality code using natural language is a high-frequency demand in the deployment of large models. Today, the IDEA Research Institute's Fengshenbang team officially open-sourced the latest code model, Ziya-Coding-34B-v1.0. We achieved a good score of 75.5 on the HumanEval Pass@1 evaluation, surpassing the score of GPT-4 (67.0) and setting a new high for known open-source models. The Fengshenbang team is providing the community with advanced large model technology and experience, helping to produce and customize more excellent vertical models, and promoting the development of the large model ecosystem.
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
更多细节可以参考我们的公众号文章：
|
| 32 |
+
|
| 33 |
+
[再创新高！姜子牙大模型开源代码大模型Ziya-Coding-34B-v1.0](https://mp.weixin.qq.com/s/tWaRF1wL3HM87ZDEawd2UA)
|
| 34 |
+
|
| 35 |
+
[姜子牙大模型系列 | 代码模型ziya-coding发布！低成本微调即可学会在专有场景编程](https://mp.weixin.qq.com/s/tWaRF1wL3HM87ZDEawd2UA)
|
| 36 |
+
|
| 37 |
+
## 软件依赖
|
| 38 |
+
```
|
| 39 |
+
pip install torch==1.12.1 tokenizers==0.13.3 git+https://github.com/huggingface/transformers
|
| 40 |
+
```
|
| 41 |
+
|
| 42 |
+
## 模型信息 Model Information
|
| 43 |
+
|
| 44 |
+
在9月初，我们开源了基于StarCoder-15B的代码模型Ziya-Coding-15B-v1，我们将训练Ziya-Coding-15B-v1积累的训练经验迁移到了新版本的训练中。
|
| 45 |
+
|
| 46 |
+
我们收集并构造了约45万涵盖了几乎所有代码相关任务的指令数据进行第一阶段的微调，这其中包括约10万的中文指令和35万的英文指令，保证了数据的多样性，在构造数据时，我们充分利用了高质量的无指令代码数据，使用LLM生成对应的指令，扩充得到了更多高质量的代码指令数据。
|
| 47 |
+
|
| 48 |
+
同时实验过程中，我们注意到，代码指令的难度和正确性是训练代码模型成功的关键。因此，我们引入了第二阶段的精调。我们使用evol-instruct的方法生成了大量高难度多要求的代码指令数据，并利用代码编译器作为反馈，筛选出能够通过编译的代码。最后利用LLM生成单元测试进一步验证代码的正确性。我们最终筛选出了46k数据，在第一阶段模型的基础上，使用较低的学习率进行微调，最终得到了我们的Ziya-coding-34B-v1.0。
|
| 49 |
+
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
In early September, we open-sourced the code model Ziya-Coding-15B-v1 based on StarCoder-15B. The training experience accumulated in training Ziya-Coding-15B-v1 was transferred to the training of the new version.
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
We collected and constructed about 450,000 instruction data covering almost all code-related tasks for the first stage of fine-tuning. This includes about 100,000 Chinese instructions and 350,000 English instructions, ensuring data diversity. When constructing the data, we made full use of high-quality non-instructional code data, used LLM to generate corresponding instructions, and expanded to obtain more high-quality code instruction data.
|
| 56 |
+
|
| 57 |
+
During the experiment, we noticed that the difficulty and correctness of code instructions are key to the successful training of code models. Therefore, we introduced a second stage of fine-tuning. We used the evol-instruct method to generate a large amount of high-difficulty, multi-requirement code instruction data, and used a code compiler as feedback to filter out code that could pass compilation. Finally, we used LLM to generate unit tests to further verify the correctness of the code. We ultimately filtered out 46k data, and on the basis of the first-stage model, we fine-tuned it with a lower learning rate to finally obtain our Ziya-coding-34B-v1.0.
|
| 58 |
+
|
| 59 |
+
### 效果评估 Performance
|
| 60 |
+
|
| 61 |
+
| Model | HumanEval(pass@1) |
|
| 62 |
+
|:----------------------------|:-----------------:|
|
| 63 |
+
| **Ziya-Coding-34B-v1.0** | **75.5%** |
|
| 64 |
+
| CodeFuse-CodeLlama-34B | 74.4% |
|
| 65 |
+
| Phind-CodeLLaMa-34B-v2 | 73.8% |
|
| 66 |
+
| WizardCoder-Python-34B-V1.0 | 73.2% |
|
| 67 |
+
| GPT-4 | 67.0% |
|
| 68 |
+
| PanGu-Coder2 15B | 61.6% |
|
| 69 |
+
| WizardCoder-15B-V1.0 | 59.8% |
|
| 70 |
+
| CodeLlama-34b-Python | 53.7% |
|
| 71 |
+
| Ziya-Coding-15B-v1 | 50.1% |
|
| 72 |
+
| CodeLlama-34b | 48.8% |
|
| 73 |
+
| GPT-3.5 | 48.1% |
|
| 74 |
+
| StarCoder-15B | 33.6% |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
其中，我们对微调数据集进行了去污处理，避免数据泄露，HumanEval的pass@1指标是贪婪生成的结果。
|
| 78 |
+
|
| 79 |
+
Prompt Format
|
| 80 |
+
```python3
|
| 81 |
+
"<human>: \nPlease Complete the given function below according to the docstring: \n{prompt}\n<bot>: \n"
|
| 82 |
+
```
|
| 83 |
+
In this process, we performed a decontamination process on the fine-tuning dataset to avoid data leakage. The pass@1 metric for HumanEval is based on the results of greedy generation.
|
| 84 |
+
|
| 85 |
+
## <span id="jump"> 使用 Usage </span>
|
| 86 |
+
```python3
|
| 87 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
| 88 |
+
import torch
|
| 89 |
+
|
| 90 |
+
device = torch.device("cuda")
|
| 91 |
+
|
| 92 |
+
prompt = "写一段快速排序"
|
| 93 |
+
model = AutoModelForCausalLM.from_pretrained("IDEA-CCNL/Ziya-Coding-34B-v1.0", torch_dtype=torch.float16, device_map="auto")
|
| 94 |
+
tokenizer = AutoTokenizer.from_pretrained("IDEA-CCNL/Ziya-Coding-34B-v1.0", use_fast=False)
|
| 95 |
+
input = f"<human>: \n{prompt}\n<bot>: \n"
|
| 96 |
+
input_ids = tokenizer(input, return_tensors="pt").input_ids.to(device)
|
| 97 |
+
generate_ids = model.generate(
|
| 98 |
+
input_ids,
|
| 99 |
+
max_new_tokens = 512,
|
| 100 |
+
do_sample = True,
|
| 101 |
+
top_p = 0.85,
|
| 102 |
+
temperature = 1.0,
|
| 103 |
+
repetition_penalty = 1.0,
|
| 104 |
+
eos_token_id = tokenizer.eos_token_id,
|
| 105 |
+
pad_token_id = tokenizer.pad_token_id,
|
| 106 |
+
)
|
| 107 |
+
output = tokenizer.batch_decode(generate_ids)[0]
|
| 108 |
+
print(output)
|
| 109 |
+
```
|
| 110 |
+
|
| 111 |
+
## 引用 Citation
|
| 112 |
+
|
| 113 |
+
如果您在您的工作中使用了我们的模型，可以引用我们的[论文](https://arxiv.org/abs/2210.08590)：
|
| 114 |
+
|
| 115 |
+
If you are using the resource for your work, please cite the our [paper](https://arxiv.org/abs/2210.08590):
|
| 116 |
+
|
| 117 |
+
```text
|
| 118 |
+
@article{fengshenbang,
|
| 119 |
+
author = {Jiaxing Zhang and Ruyi Gan and Junjie Wang and Yuxiang Zhang and Lin Zhang and Ping Yang and Xinyu Gao and Ziwei Wu and Xiaoqun Dong and Junqing He and Jianheng Zhuo and Qi Yang and Yongfeng Huang and Xiayu Li and Yanghan Wu and Junyu Lu and Xinyu Zhu and Weifeng Chen and Ting Han and Kunhao Pan and Rui Wang and Hao Wang and Xiaojun Wu and Zhongshen Zeng and Chongpei Chen},
|
| 120 |
+
title = {Fengshenbang 1.0: Being the Foundation of Chinese Cognitive Intelligence},
|
| 121 |
+
journal = {CoRR},
|
| 122 |
+
volume = {abs/2209.02970},
|
| 123 |
+
year = {2022}
|
| 124 |
+
}
|
| 125 |
+
```
|
| 126 |
+
|
| 127 |
+
You can also cite our [website](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
|
| 128 |
+
|
| 129 |
+
欢迎引用我们的[网站](https://github.com/IDEA-CCNL/Fengshenbang-LM/):
|
| 130 |
+
```text
|
| 131 |
+
@misc{Fengshenbang-LM,
|
| 132 |
+
title={Fengshenbang-LM},
|
| 133 |
+
author={IDEA-CCNL},
|
| 134 |
+
year={2021},
|
| 135 |
+
howpublished={\url{https://github.com/IDEA-CCNL/Fengshenbang-LM}},
|
| 136 |
+
}
|
| 137 |
+
```
|
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/cognitive_comp/liuyibo/cg/FastChat_project/FastChat/Mindbot/base_codellama_python_common_data_code_dialogue_65W_Character_2node_checkpoint-1260_total_evolInstruct_code_2node/checkpoint-240",
|
| 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 |
+
"pretraining_tp": 1,
|
| 18 |
+
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_scaling": null,
|
| 20 |
+
"rope_theta": 1000000,
|
| 21 |
+
"tie_word_embeddings": false,
|
| 22 |
+
"torch_dtype": "bfloat16",
|
| 23 |
+
"transformers_version": "4.32.1",
|
| 24 |
+
"use_cache": false,
|
| 25 |
+
"vocab_size": 32000
|
| 26 |
+
}
|
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": "4.32.1"
|
| 6 |
+
}
|
pytorch_model-00025-of-00025.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:713cc74edf8b0534bff4aef27cbd2573f103d58786efdafa4f1792cb5c837f72
|
| 3 |
+
size 885049454
|
pytorch_model.bin.index.json
ADDED
|
@@ -0,0 +1,442 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 67487940608
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "pytorch_model-00025-of-00025.bin",
|
| 7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00025.bin",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00025.bin",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00025.bin",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00025.bin",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00025.bin",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00025.bin",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00025.bin",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00025.bin",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00025.bin",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00025.bin",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00025.bin",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00025.bin",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00025.bin",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00025.bin",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00025.bin",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00025.bin",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00025.bin",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00025.bin",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00006-of-00025.bin",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00006-of-00025.bin",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00007-of-00025.bin",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00007-of-00025.bin",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00007-of-00025.bin",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00007-of-00025.bin",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00008-of-00025.bin",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00008-of-00025.bin",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00007-of-00025.bin",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00008-of-00025.bin",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00008-of-00025.bin",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00009-of-00025.bin",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00009-of-00025.bin",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00008-of-00025.bin",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00009-of-00025.bin",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00009-of-00025.bin",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00010-of-00025.bin",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00010-of-00025.bin",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00009-of-00025.bin",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00010-of-00025.bin",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00010-of-00025.bin",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00011-of-00025.bin",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00011-of-00025.bin",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00010-of-00025.bin",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00025.bin",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00025.bin",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00011-of-00025.bin",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00011-of-00025.bin",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00012-of-00025.bin",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00012-of-00025.bin",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00011-of-00025.bin",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00012-of-00025.bin",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00012-of-00025.bin",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00013-of-00025.bin",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00013-of-00025.bin",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00012-of-00025.bin",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00013-of-00025.bin",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00013-of-00025.bin",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00014-of-00025.bin",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00014-of-00025.bin",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00013-of-00025.bin",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00014-of-00025.bin",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00014-of-00025.bin",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00015-of-00025.bin",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00015-of-00025.bin",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00014-of-00025.bin",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00015-of-00025.bin",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00015-of-00025.bin",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00016-of-00025.bin",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00016-of-00025.bin",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00015-of-00025.bin",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00025.bin",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00025.bin",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00025.bin",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00016-of-00025.bin",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00016-of-00025.bin",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00017-of-00025.bin",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00017-of-00025.bin",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00016-of-00025.bin",
|
| 242 |
+
"model.layers.32.input_layernorm.weight": "pytorch_model-00017-of-00025.bin",
|
| 243 |
+
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 244 |
+
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 245 |
+
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 246 |
+
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00017-of-00025.bin",
|
| 247 |
+
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 248 |
+
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 249 |
+
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 250 |
+
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 251 |
+
"model.layers.33.input_layernorm.weight": "pytorch_model-00018-of-00025.bin",
|
| 252 |
+
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 253 |
+
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 254 |
+
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 255 |
+
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00018-of-00025.bin",
|
| 256 |
+
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 257 |
+
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 258 |
+
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 259 |
+
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00017-of-00025.bin",
|
| 260 |
+
"model.layers.34.input_layernorm.weight": "pytorch_model-00018-of-00025.bin",
|
| 261 |
+
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 262 |
+
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 263 |
+
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 264 |
+
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00018-of-00025.bin",
|
| 265 |
+
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 266 |
+
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 267 |
+
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 268 |
+
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 269 |
+
"model.layers.35.input_layernorm.weight": "pytorch_model-00019-of-00025.bin",
|
| 270 |
+
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 271 |
+
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 272 |
+
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 273 |
+
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00019-of-00025.bin",
|
| 274 |
+
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 275 |
+
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 276 |
+
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 277 |
+
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00018-of-00025.bin",
|
| 278 |
+
"model.layers.36.input_layernorm.weight": "pytorch_model-00019-of-00025.bin",
|
| 279 |
+
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 280 |
+
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 281 |
+
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 282 |
+
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00019-of-00025.bin",
|
| 283 |
+
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 284 |
+
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 285 |
+
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 286 |
+
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 287 |
+
"model.layers.37.input_layernorm.weight": "pytorch_model-00020-of-00025.bin",
|
| 288 |
+
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 289 |
+
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 290 |
+
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 291 |
+
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00020-of-00025.bin",
|
| 292 |
+
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 293 |
+
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 294 |
+
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 295 |
+
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00019-of-00025.bin",
|
| 296 |
+
"model.layers.38.input_layernorm.weight": "pytorch_model-00020-of-00025.bin",
|
| 297 |
+
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 298 |
+
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 299 |
+
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 300 |
+
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00020-of-00025.bin",
|
| 301 |
+
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 302 |
+
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 303 |
+
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 304 |
+
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 305 |
+
"model.layers.39.input_layernorm.weight": "pytorch_model-00021-of-00025.bin",
|
| 306 |
+
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 307 |
+
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 308 |
+
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 309 |
+
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00021-of-00025.bin",
|
| 310 |
+
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 311 |
+
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 312 |
+
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 313 |
+
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00020-of-00025.bin",
|
| 314 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00025.bin",
|
| 315 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 316 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 317 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 318 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00025.bin",
|
| 319 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 320 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 321 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 322 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 323 |
+
"model.layers.40.input_layernorm.weight": "pytorch_model-00021-of-00025.bin",
|
| 324 |
+
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 325 |
+
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 326 |
+
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 327 |
+
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00021-of-00025.bin",
|
| 328 |
+
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 329 |
+
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 330 |
+
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 331 |
+
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 332 |
+
"model.layers.41.input_layernorm.weight": "pytorch_model-00022-of-00025.bin",
|
| 333 |
+
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 334 |
+
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 335 |
+
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 336 |
+
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00022-of-00025.bin",
|
| 337 |
+
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 338 |
+
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 339 |
+
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 340 |
+
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00021-of-00025.bin",
|
| 341 |
+
"model.layers.42.input_layernorm.weight": "pytorch_model-00022-of-00025.bin",
|
| 342 |
+
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 343 |
+
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 344 |
+
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 345 |
+
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00022-of-00025.bin",
|
| 346 |
+
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 347 |
+
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 348 |
+
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 349 |
+
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 350 |
+
"model.layers.43.input_layernorm.weight": "pytorch_model-00023-of-00025.bin",
|
| 351 |
+
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 352 |
+
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 353 |
+
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 354 |
+
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00023-of-00025.bin",
|
| 355 |
+
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 356 |
+
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 357 |
+
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 358 |
+
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00022-of-00025.bin",
|
| 359 |
+
"model.layers.44.input_layernorm.weight": "pytorch_model-00023-of-00025.bin",
|
| 360 |
+
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 361 |
+
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 362 |
+
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 363 |
+
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00023-of-00025.bin",
|
| 364 |
+
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 365 |
+
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 366 |
+
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 367 |
+
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 368 |
+
"model.layers.45.input_layernorm.weight": "pytorch_model-00024-of-00025.bin",
|
| 369 |
+
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 370 |
+
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 371 |
+
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 372 |
+
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00024-of-00025.bin",
|
| 373 |
+
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 374 |
+
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 375 |
+
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 376 |
+
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00023-of-00025.bin",
|
| 377 |
+
"model.layers.46.input_layernorm.weight": "pytorch_model-00024-of-00025.bin",
|
| 378 |
+
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 379 |
+
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 380 |
+
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 381 |
+
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00024-of-00025.bin",
|
| 382 |
+
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 383 |
+
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 384 |
+
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 385 |
+
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 386 |
+
"model.layers.47.input_layernorm.weight": "pytorch_model-00025-of-00025.bin",
|
| 387 |
+
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00025-of-00025.bin",
|
| 388 |
+
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 389 |
+
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 390 |
+
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00025-of-00025.bin",
|
| 391 |
+
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 392 |
+
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 393 |
+
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 394 |
+
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00024-of-00025.bin",
|
| 395 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00004-of-00025.bin",
|
| 396 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 397 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 398 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 399 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00004-of-00025.bin",
|
| 400 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 401 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 402 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 403 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00025.bin",
|
| 404 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00025.bin",
|
| 405 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 406 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 407 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 408 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00025.bin",
|
| 409 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 410 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 411 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 412 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 413 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00005-of-00025.bin",
|
| 414 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 415 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 416 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 417 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00005-of-00025.bin",
|
| 418 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 419 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 420 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 421 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00025.bin",
|
| 422 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00025.bin",
|
| 423 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 424 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 425 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 426 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00025.bin",
|
| 427 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 428 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 429 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 430 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 431 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00006-of-00025.bin",
|
| 432 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00006-of-00025.bin",
|
| 433 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 434 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 435 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00006-of-00025.bin",
|
| 436 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 437 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 438 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 439 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00025.bin",
|
| 440 |
+
"model.norm.weight": "pytorch_model-00025-of-00025.bin"
|
| 441 |
+
}
|
| 442 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
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 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"legacy": null,
|
| 22 |
+
"model_max_length": 4096,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"sp_model_kwargs": {},
|
| 26 |
+
"spaces_between_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 28 |
+
"unk_token": {
|
| 29 |
+
"__type": "AddedToken",
|
| 30 |
+
"content": "<unk>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
},
|
| 36 |
+
"use_default_system_prompt": true
|
| 37 |
+
}
|