Commit
•
deb3bfe
1
Parent(s):
19c8977
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +274 -0
- config.json +30 -0
- generation_config.json +6 -0
- model.safetensors.index.json +1002 -0
- output-00001-of-00004.safetensors +3 -0
- output-00002-of-00004.safetensors +3 -0
- output-00003-of-00004.safetensors +3 -0
- output-00004-of-00004.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
img/case.png filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,274 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
<div align="center">
|
| 5 |
+
<h1>
|
| 6 |
+
Chinese-Mixtral-8x7B
|
| 7 |
+
</h1>
|
| 8 |
+
</div>
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
<div align="center">
|
| 13 |
+
<a href="https://github.com/HIT-SCIR/Chinese-Mixtral-8x7B/pulls">
|
| 14 |
+
<image src="https://img.shields.io/badge/PRs-welcome-brightgreen"></image>
|
| 15 |
+
<image src="https://img.shields.io/badge/License-Apache_2.0-green.svg"></image>
|
| 16 |
+
</a>
|
| 17 |
+
</div>
|
| 18 |
+
|
| 19 |
+
## 🚀 介绍
|
| 20 |
+
|
| 21 |
+
本项目基于Mistral发布的模型[Mixtral-8x7B](https://mistral.ai/news/mixtral-of-experts/)进行了中文扩词表增量预训练，希望进一步促进中文自然语言处理社区对MoE模型的研究。我们扩充后的词表显著提高了模型对中文的编解码效率，并通过大规模开源语料对扩词表模型进行增量预训练，使模型具备了强大的中文生成和理解能力。
|
| 22 |
+
|
| 23 |
+
项目开源内容：
|
| 24 |
+
|
| 25 |
+
- 中文Mixtral-8x7B扩词表大模型
|
| 26 |
+
- 扩词表增量预训练代码
|
| 27 |
+
|
| 28 |
+
> 请注意，Chinese-Mixtral-8x7B仍然可能生成包含事实性错误的误导性回复或包含偏见/歧视的有害内容，请谨慎鉴别和使用生成的内容，请勿将生成的有害内容传播至互联网。
|
| 29 |
+
|
| 30 |
+
## 📥 模型下载
|
| 31 |
+
|
| 32 |
+
本项目使用QLoRA进行训练，LoRA权重与合并权重后的模型分别开源，您可以根据自己的需求选择下载：
|
| 33 |
+
|
| 34 |
+
| 模型名称 | 模型大小 | 下载地址 | 备注 |
|
| 35 |
+
|:----------------------------:|:-----:|:-----------------------------------------------------------------------------:|:-------------------------------------------------------------------------------------------------------------------:|
|
| 36 |
+
| Chinese-Mixtral-8x7B | 88GB | [🤗HuggingFace](https://huggingface.co/HIT-SCIR/Chinese-Mixtral-8x7B) | 中文扩词表完整模型，可以直接使用 |
|
| 37 |
+
| Chinese-Mixtral-8x7B-adapter | 2.7GB | [🤗HuggingFace](https://huggingface.co/HIT-SCIR/Chinese-Mixtral-8x7B-adapter) | LoRA权重，需要与原版Mixtral-8x7B进行合并才可以使用，合并脚本请参考[这里](https://gist.github.com/ChrisHayduk/1a53463331f52dca205e55982baf9930) |
|
| 38 |
+
|
| 39 |
+
## 💻 模型推理
|
| 40 |
+
|
| 41 |
+
Chinese-Mixtral-8x7B支持完整的Mixtral-8x7B模型生态，包括使用`vLLM`、`Flash Attention 2`进行加速，使用`bitsandbytes`进行模型量化等。以下是使用Chinese-Mixtral-8x7B进行推理的代码示例。
|
| 42 |
+
|
| 43 |
+
使用Flash Attention 2：
|
| 44 |
+
```python
|
| 45 |
+
import torch
|
| 46 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 47 |
+
|
| 48 |
+
model_id = "HIT-SCIR/Chinese-Mixtral-8x7B"
|
| 49 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 50 |
+
|
| 51 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, attn_implementation="flash_attention_2", torch_dtype=torch.bfloat16, device_map="auto")
|
| 52 |
+
|
| 53 |
+
text = "我的名字是"
|
| 54 |
+
inputs = tokenizer(text, return_tensors="pt").to(0)
|
| 55 |
+
|
| 56 |
+
outputs = model.generate(**inputs, max_new_tokens=20)
|
| 57 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
| 58 |
+
```
|
| 59 |
+
|
| 60 |
+
使用4bit量化：
|
| 61 |
+
```python
|
| 62 |
+
import torch
|
| 63 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 64 |
+
|
| 65 |
+
model_id = "HIT-SCIR/Chinese-Mixtral-8x7B"
|
| 66 |
+
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
| 67 |
+
|
| 68 |
+
model = AutoModelForCausalLM.from_pretrained(model_id, load_in_4bit=True, device_map="auto")
|
| 69 |
+
|
| 70 |
+
text = "我的名字是"
|
| 71 |
+
inputs = tokenizer(text, return_tensors="pt").to(0)
|
| 72 |
+
|
| 73 |
+
outputs = model.generate(**inputs, max_new_tokens=20)
|
| 74 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
| 75 |
+
```
|
| 76 |
+
|
| 77 |
+
请注意，Chinese-Mixtral-8x7B为基座模型，没有经过指令微调，因此指令遵循能力有限。您可以参考[微调](#微调)一节对模型进行微调。
|
| 78 |
+
|
| 79 |
+
## 📈 模型性能
|
| 80 |
+
|
| 81 |
+
### 模型综合能力
|
| 82 |
+
|
| 83 |
+
我们分别使用以下评测数据集对Chinese-Mixtral-8x7B进行评测：
|
| 84 |
+
|
| 85 |
+
- C-Eval：一个全面的中文基础模型评估套件。它包含了13948个多项选择题，涵盖了52个不同的学科和四个难度级别。
|
| 86 |
+
- CMMLU：一个综合性的中文评估基准，专门用于评估语言模型在中文语境下的知识和推理能力，涵盖了从基础学科到高级专业水平的67个主题。
|
| 87 |
+
- MMLU：一个包含57个多选任务的英文评测数据集，涵盖了初等数学、美国历史、计算机科学、法律等，难度覆盖高中水平到专家水平，是目前主流的LLM评测数据集之一。
|
| 88 |
+
- HellaSwag：一个极具挑战的英文NLI评测数据集，每一个问题都需要对上下文进行深入理解，而不能基于常识进行回答。
|
| 89 |
+
|
| 90 |
+
根据Mistral发布的[技术报告](https://arxiv.org/pdf/2401.04088.pdf)，Mixtral-8x7B在推理时将激活13B参数。下表为Chinese-Mixtral-8x7B与其他13B规模的中文扩词表模型在各个评测数据集上的5-shot结果：
|
| 91 |
+
|
| 92 |
+
| 模型名称 | 增量训练语料 | C-Eval<br>(中文) | CMMLU<br>(中文) | MMLU<br>(英文) | HellaSwag<br>(英文) |
|
| 93 |
+
|:-----------------------------------------------------------------------------------------------:|:-----------------:|:--------------:|:-------------:|:------------:|:-----------------:|
|
| 94 |
+
| [IDEA-CCNL/Ziya2-13B-Base](https://huggingface.co/IDEA-CCNL/Ziya2-13B-Base) | 650B Token | 59.29 | 60.93 | 59.86 | 58.90 |
|
| 95 |
+
| [TigerResearch/tigerbot-13b-base-v3](https://huggingface.co/TigerResearch/tigerbot-13b-base-v3) | 500B Token | 50.52 | 51.65 | 53.46 | 59.16 |
|
| 96 |
+
| [Linly-AI/Chinese-LLaMA-2-13B-hf](https://huggingface.co/Linly-AI/Chinese-LLaMA-2-13B-hf) | 11B Token | 42.57 | 41.95 | 51.32 | 59.05 |
|
| 97 |
+
| [hfl/chinese-llama-2-13b](https://huggingface.co/hfl/chinese-llama-2-13b) | 约30B Token(120GB) | 41.90 | 42.08 | 51.92 | 59.28 |
|
| 98 |
+
| **Chinese-Mixtral-8x7B(本项目)** | 42B Token | 52.08 | 51.08 | 69.80 | 65.69 |
|
| 99 |
+
|
| 100 |
+
在中文知识和理解方面，我们的Chinese-Mixtral-8x7B与TigerBot-13B-Base-v3性能相当。由于Chinese-Mixtral-8x7B的训练数据量仅为TigerBot-13B-Base-v3的8%，我们的模型仍有进一步提升的空间。与此同时，得益于原版Mixtral-8x7B模型强大的性能，我们的Chinese-Mixtral-8x7B达到了各个扩词表模型的最强英文水平。
|
| 101 |
+
|
| 102 |
+
> 由于不同版本的评测脚本实现细节有细微差异，为了保证评测结果的一致性和公平性，我们的评测脚本统一使用EleutherAI发布的lm-evaluation-harness，commit hash为[28ec7fa](https://github.com/EleutherAI/lm-evaluation-harness/tree/28ec7fa950346b5a895e85e1f3edd5648168acc4)。
|
| 103 |
+
|
| 104 |
+
### 模型生成效果
|
| 105 |
+
|
| 106 |
+
下表为各个扩词表模型的生成效果。由于部分模型的预训练语料未使用`eos_token`进行分隔，我们采用了`max_tokens = 100`对生成文本进行截断。我们的采样参数为`temperature = 0.8, top_p = 0.9`。
|
| 107 |
+
|
| 108 |
+
|
| 109 |
+
|
| 110 |
+
### 中文编解码效率
|
| 111 |
+
|
| 112 |
+
针对中文编解码效率，我们使用各个扩词表模型的分词器对[SkyPile](https://huggingface.co/datasets/Skywork/SkyPile-150B)数据集的一个切片（2023-06_zh_head_0000.jsonl）进行编码，对比了各个分词器输出的中文文本Token量：
|
| 113 |
+
|
| 114 |
+
| 模型名称 | 模型类别 | 词表大小 | 中文文本Token量 | 编解码效率 |
|
| 115 |
+
|:----------------------------------:|:-------:|:-----:|:----------:|:-------:|
|
| 116 |
+
| meta-llama/Llama-2-13B-hf | LLaMA | 32000 | 780M | 低 |
|
| 117 |
+
| mistralai/Mixtral-8x7B-v0.1 | Mixtral | 32000 | 606M | 低 |
|
| 118 |
+
| Linly-AI/Chinese-LLaMA-2-13B-hf | LLaMA | 40076 | 532M | 中 |
|
| 119 |
+
| IDEA-CCNL/Ziya2-13B-Base | LLaMA | 39424 | 532M | 中 |
|
| 120 |
+
| hfl/chinese-llama-2-13b | LLaMA | 55296 | 365M | 高 |、
|
| 121 |
+
| TigerResearch/tigerbot-13b-base-v3 | LLaMA | 65112 | 342M | 高 |
|
| 122 |
+
| **Chinese-Mixtral-8x7B(本项目)** | Mixtral | 57000 | 355M | 高 |
|
| 123 |
+
|
| 124 |
+
在约1.4GB的测试文本中，我们的Chinese-Mixtral-8x7B中文编解码效率仅次于TigerBot-13B-Base-v3，较原模型提高了41.5%。这有利于加速中文文本的推理速度，并在In-Context Learning、Chain-of-Thought等场景中节省序列长度，有利于提高复杂推理任务的性能。
|
| 125 |
+
|
| 126 |
+
## ⚙️ 训练细节
|
| 127 |
+
|
| 128 |
+
<details>
|
| 129 |
+
<summary>
|
| 130 |
+
|
| 131 |
+
### 词表扩充
|
| 132 |
+
|
| 133 |
+
</summary>
|
| 134 |
+
|
| 135 |
+
我们使用`sentencepiece`在12G知乎数据和2G悟道数据上训练中文BPE词表。我们在训练词表时分别枚举了中文单字Token数量以及中文总Token数量，并对二者进行组合，得到了数百个大小、内容各异的词表。为了得到最适合的词表，我们通过Zheng Bo等人提出的[ALP](https://arxiv.org/pdf/2109.07306.pdf)计算这些词表的中文词汇能力。ALP通过计算特定语言的子词切分粒度，并对词表的中低频子词进行惩罚，是一种方便快捷的衡量特定语言词汇能力的指标。
|
| 136 |
+
|
| 137 |
+
我们在书籍和百科语料上评估了不同词表的ALP值。图示中，四条曲线分别代表四种中文单字Token数量的词表（4451、5435、6414和7434）。为了避免词表过小导致中文压缩率过低，以及词表过大导致embedding层过于稀疏，我们选取ALP曲线的拐点，对应向词表中新增25000个中文Token。在此基础上，我们选择了四条曲线中ALP最大者，即新增6414个中文单字Token的词表，作为最终Chinese-Mixtral-8x7B选用的词表。
|
| 138 |
+
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
在获得新词表后，我们需要对embedding和lm_head层进行扩充和初始化。我们使用新Token在旧embedding层中的词嵌入平均值对扩充部分进行初始化。在我们的前期实验中，这种方法略优于HuggingFace的默认实现，即使用固定的正态分布进行初始化。
|
| 142 |
+
|
| 143 |
+
</details>
|
| 144 |
+
|
| 145 |
+
<details>
|
| 146 |
+
<summary>
|
| 147 |
+
|
| 148 |
+
### 增量预训练
|
| 149 |
+
|
| 150 |
+
</summary>
|
| 151 |
+
|
| 152 |
+
Mixtral-8x7B模型参数量为46.7B，全参数训练需要同时使用多种并行策略，在训练资源受限的情况下时间成本过高。因此我们采用HuggingFace官方推荐的方法，使用QLoRA对模型进行训练。QLoRA在LoRA低秩分解的基础上，通过引入4位量化、双重量化和利用NVIDIA统一内存进行分页，进一步减少了训练所需显存，同时保持了与全参数训练相当的性能。
|
| 153 |
+
|
| 154 |
+
我们参考Yiming Cui等人[对LoRA的设置](https://github.com/ymcui/Chinese-LLaMA-Alpaca-2/blob/main/scripts/training/run_pt.sh)，对原模型所有Linear层应用低秩分解，并将扩增后的embedding和lm_head层的参数设置为可训练。对于模型主体，我们采用NF4格式进行量化，这种格式可以使得量化后的数据与量化前具有同等的数据分布，模型的权重信息损失更少。
|
| 155 |
+
|
| 156 |
+
#### 环境准备
|
| 157 |
+
|
| 158 |
+
我们建议使用Python 3.10 + torch 2.0.1
|
| 159 |
+
|
| 160 |
+
```shell
|
| 161 |
+
# Pytorch + Transformers
|
| 162 |
+
$ pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2
|
| 163 |
+
$ pip install transformers==4.36.2 datasets evaluate peft accelerate gradio optimum sentencepiece
|
| 164 |
+
$ pip install jupyterlab scikit-learn pandas matplotlib tensorboard nltk rouge bitsandbytes fire
|
| 165 |
+
# DeepSpeed
|
| 166 |
+
$ git clone https://github.com/microsoft/DeepSpeed.git
|
| 167 |
+
$ cd DeepSpeed
|
| 168 |
+
$ DS_BUILD_FUSED_ADAM=1 pip3 install .
|
| 169 |
+
# Flash Attention
|
| 170 |
+
$ pip install flash-attn --no-build-isolation
|
| 171 |
+
```
|
| 172 |
+
|
| 173 |
+
#### 数据集下载
|
| 174 |
+
|
| 175 |
+
我们基于现有的开源数据集训练了Chinese-Mixtral-8x7B，数据集包括：
|
| 176 |
+
|
| 177 |
+
| 数据集名称 | 数据集语言 |使用数据量| 备注 |
|
| 178 |
+
|:----------------------------------------------------------------------------:|:-----:|:----------------:|:-----:|
|
| 179 |
+
| [Skywork/SkyPile-150B](https://huggingface.co/datasets/Skywork/SkyPile-150B) | 中文 |30B| 仅使用2022 + 2023年的数据 |
|
| 180 |
+
| [DKYoon/SlimPajama-6B](https://huggingface.co/datasets/DKYoon/SlimPajama-6B) | 英文 |12B| 数据集重复2 Epoch |
|
| 181 |
+
|
| 182 |
+
通过`data/download.py`将数据集下载到`data`中。针对Slimpajama数据集，需要使用`data/parquet2jsonl.py`将原始数据集转换为`jsonl`格式。
|
| 183 |
+
|
| 184 |
+
下载后的数据集为多个jsonl文件的分片，使用`cat`将多个分片合并为一个jsonl文件。
|
| 185 |
+
|
| 186 |
+
```shell
|
| 187 |
+
$ cat *.jsonl > all.jsonl
|
| 188 |
+
```
|
| 189 |
+
|
| 190 |
+
通过`split`将jsonl切分为train和valid集合。本项目中train和valid的行数比例为999:1。
|
| 191 |
+
|
| 192 |
+
```shell
|
| 193 |
+
$ wc -l all.jsonl # 计算数据集总行数
|
| 194 |
+
$ split -l <lines> all.jsonl # 按999:1计算train/valid行数，进行切分
|
| 195 |
+
$ mv xaa DKYoon-SlimPajama-6B-train.jsonl # 重命名
|
| 196 |
+
$ mv xab DKYoon-SlimPajama-6B-dev.jsonl
|
| 197 |
+
```
|
| 198 |
+
|
| 199 |
+
#### 数据集预处理
|
| 200 |
+
|
| 201 |
+
将数据集名称和路径注册到`data/datasets.toml`中：
|
| 202 |
+
|
| 203 |
+
```toml
|
| 204 |
+
[DKYoon-SlimPajama-6B] # 数据集名称
|
| 205 |
+
splits = ["train", "dev"] # 数据集train/valid集合
|
| 206 |
+
root = "{DATA_DIR}/en/{name}" # 数据集根目录
|
| 207 |
+
doc = "{name}-{split}" # 数据集文件名
|
| 208 |
+
encoded = "encoded-{name}-{split}" # 预处理保存位置
|
| 209 |
+
```
|
| 210 |
+
|
| 211 |
+
使用`data/preprocess_datasets.py`对数据集进行子词切分，从而加快训练速度。
|
| 212 |
+
|
| 213 |
+
```shell
|
| 214 |
+
$ python data/preprocess_datasets.py --ds_name SkyPile-150B-2023 --tokenizer_name_or_path tokenizer/Mixtral-8x7B-v0.1-vocab
|
| 215 |
+
$ python data/preprocess_datasets.py --ds_name DKYoon-SlimPajama-6B --tokenizer_name_or_path tokenizer/Mixtral-8x7B-v0.1-vocab
|
| 216 |
+
```
|
| 217 |
+
|
| 218 |
+
在进行子词切分后，可以使用`data/utils.py`查看各个数据集的token总量：
|
| 219 |
+
|
| 220 |
+
```shell
|
| 221 |
+
$ python data/utils.py
|
| 222 |
+
```
|
| 223 |
+
|
| 224 |
+
#### 开始训练
|
| 225 |
+
|
| 226 |
+
训练启动脚本为`scripts/train.sh`。可以通过修改其中的`TRAIN_DATASETS`修改训练数据集和数据集比例：
|
| 227 |
+
|
| 228 |
+
```shell
|
| 229 |
+
TRAIN_DATASETS=(
|
| 230 |
+
1:SkyPile-150B-2022 # 使用全量SkyPile-150B-2022
|
| 231 |
+
0.1:SkyPile-150B-2023 # 使用SkyPile-150B-2023的10%数据
|
| 232 |
+
1:DKYoon-SlimPajama-6B # 使用全量DKYoon-SlimPajama-6B
|
| 233 |
+
)
|
| 234 |
+
```
|
| 235 |
+
|
| 236 |
+
如果您使用SLURM集群管理系统，可以通过`sbatch`进行提交：
|
| 237 |
+
|
| 238 |
+
```shell
|
| 239 |
+
$ sbatch scripts/train.sh
|
| 240 |
+
```
|
| 241 |
+
|
| 242 |
+
如果没有SLURM或希望通过命令行启动训练，您可以直接提取`scripts/train.sh`中的`torchrun`开始训练。
|
| 243 |
+
|
| 244 |
+
</details>
|
| 245 |
+
|
| 246 |
+
<details>
|
| 247 |
+
<summary>
|
| 248 |
+
|
| 249 |
+
### 微调
|
| 250 |
+
|
| 251 |
+
</summary>
|
| 252 |
+
|
| 253 |
+
本项目发布的Chinese-Mixtral-8x7B为基座模型，没有经过微调。如果您希望使用Chinese-Mixtral-8x7B进行下游任务微调或SFT，可以参考HuggingFace给出Mixtral-8x7B的QLoRA微调脚本进行训练：[HuggingFace的官方示例代码](https://github.com/huggingface/trl/blob/main/examples/scripts/sft.py)。
|
| 254 |
+
|
| 255 |
+
</details>
|
| 256 |
+
|
| 257 |
+
## ✒️ 引用
|
| 258 |
+
|
| 259 |
+
如果您觉得本项目对您的研究有所帮助或使用了本项目的代码，请引用本项目：
|
| 260 |
+
|
| 261 |
+
```bibtex
|
| 262 |
+
@misc{Chinese-Mixtral-8x7B,
|
| 263 |
+
author = {HIT-SCIR},
|
| 264 |
+
title = {Chinese-Mixtral-8x7B: An Open-Source Mixture-of-Experts LLM},
|
| 265 |
+
year = {2024},
|
| 266 |
+
publisher = {GitHub},
|
| 267 |
+
journal = {GitHub repository},
|
| 268 |
+
howpublished = {\url{https://github.com/HIT-SCIR/Chinese-Mixtral-8x7B}}
|
| 269 |
+
}
|
| 270 |
+
```
|
| 271 |
+
|
| 272 |
+
## 🌟 Star History
|
| 273 |
+
|
| 274 |
+
[](https://star-history.com/#HIT-SCIR/Chinese-Mixtral-8x7B&Date)
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/ssd/home/syji/hf_model/mistralai/Mixtral-8x7B-v0.1-vocab",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MixtralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 1,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 4096,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 14336,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"model_type": "mixtral",
|
| 15 |
+
"num_attention_heads": 32,
|
| 16 |
+
"num_experts_per_tok": 2,
|
| 17 |
+
"num_hidden_layers": 32,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
+
"num_local_experts": 8,
|
| 20 |
+
"output_router_logits": false,
|
| 21 |
+
"rms_norm_eps": 1e-05,
|
| 22 |
+
"rope_theta": 1000000.0,
|
| 23 |
+
"router_aux_loss_coef": 0.02,
|
| 24 |
+
"sliding_window": null,
|
| 25 |
+
"tie_word_embeddings": false,
|
| 26 |
+
"torch_dtype": "bfloat16",
|
| 27 |
+
"transformers_version": "4.36.1",
|
| 28 |
+
"use_cache": true,
|
| 29 |
+
"vocab_size": 57000
|
| 30 |
+
}
|
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": "4.36.1"
|
| 6 |
+
}
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1002 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 93815185408
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00019-of-00019.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00019.safetensors",
|
| 8 |
+
"model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors",
|
| 9 |
+
"model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors",
|
| 10 |
+
"model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors",
|
| 11 |
+
"model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors",
|
| 12 |
+
"model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors",
|
| 13 |
+
"model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors",
|
| 14 |
+
"model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors",
|
| 15 |
+
"model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors",
|
| 16 |
+
"model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors",
|
| 17 |
+
"model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors",
|
| 18 |
+
"model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors",
|
| 19 |
+
"model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00019.safetensors",
|
| 20 |
+
"model.layers.0.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00019.safetensors",
|
| 21 |
+
"model.layers.0.block_sparse_moe.experts.4.w2.weight": "model-00001-of-00019.safetensors",
|
| 22 |
+
"model.layers.0.block_sparse_moe.experts.4.w3.weight": "model-00001-of-00019.safetensors",
|
| 23 |
+
"model.layers.0.block_sparse_moe.experts.5.w1.weight": "model-00001-of-00019.safetensors",
|
| 24 |
+
"model.layers.0.block_sparse_moe.experts.5.w2.weight": "model-00001-of-00019.safetensors",
|
| 25 |
+
"model.layers.0.block_sparse_moe.experts.5.w3.weight": "model-00001-of-00019.safetensors",
|
| 26 |
+
"model.layers.0.block_sparse_moe.experts.6.w1.weight": "model-00001-of-00019.safetensors",
|
| 27 |
+
"model.layers.0.block_sparse_moe.experts.6.w2.weight": "model-00001-of-00019.safetensors",
|
| 28 |
+
"model.layers.0.block_sparse_moe.experts.6.w3.weight": "model-00001-of-00019.safetensors",
|
| 29 |
+
"model.layers.0.block_sparse_moe.experts.7.w1.weight": "model-00001-of-00019.safetensors",
|
| 30 |
+
"model.layers.0.block_sparse_moe.experts.7.w2.weight": "model-00001-of-00019.safetensors",
|
| 31 |
+
"model.layers.0.block_sparse_moe.experts.7.w3.weight": "model-00001-of-00019.safetensors",
|
| 32 |
+
"model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00019.safetensors",
|
| 33 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00019.safetensors",
|
| 34 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00019.safetensors",
|
| 35 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00019.safetensors",
|
| 36 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00019.safetensors",
|
| 37 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00019.safetensors",
|
| 38 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00019.safetensors",
|
| 39 |
+
"model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00019.safetensors",
|
| 40 |
+
"model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00019.safetensors",
|
| 41 |
+
"model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00019.safetensors",
|
| 42 |
+
"model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00019.safetensors",
|
| 43 |
+
"model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00019.safetensors",
|
| 44 |
+
"model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00019.safetensors",
|
| 45 |
+
"model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00019.safetensors",
|
| 46 |
+
"model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00019.safetensors",
|
| 47 |
+
"model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00019.safetensors",
|
| 48 |
+
"model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00019.safetensors",
|
| 49 |
+
"model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00019.safetensors",
|
| 50 |
+
"model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00019.safetensors",
|
| 51 |
+
"model.layers.1.block_sparse_moe.experts.4.w1.weight": "model-00001-of-00019.safetensors",
|
| 52 |
+
"model.layers.1.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00019.safetensors",
|
| 53 |
+
"model.layers.1.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors",
|
| 54 |
+
"model.layers.1.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors",
|
| 55 |
+
"model.layers.1.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors",
|
| 56 |
+
"model.layers.1.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors",
|
| 57 |
+
"model.layers.1.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00019.safetensors",
|
| 58 |
+
"model.layers.1.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00019.safetensors",
|
| 59 |
+
"model.layers.1.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00019.safetensors",
|
| 60 |
+
"model.layers.1.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00019.safetensors",
|
| 61 |
+
"model.layers.1.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00019.safetensors",
|
| 62 |
+
"model.layers.1.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00019.safetensors",
|
| 63 |
+
"model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00019.safetensors",
|
| 64 |
+
"model.layers.1.input_layernorm.weight": "model-00002-of-00019.safetensors",
|
| 65 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00019.safetensors",
|
| 66 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00019.safetensors",
|
| 67 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00019.safetensors",
|
| 68 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00019.safetensors",
|
| 69 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00019.safetensors",
|
| 70 |
+
"model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors",
|
| 71 |
+
"model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors",
|
| 72 |
+
"model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00019.safetensors",
|
| 73 |
+
"model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors",
|
| 74 |
+
"model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors",
|
| 75 |
+
"model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors",
|
| 76 |
+
"model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors",
|
| 77 |
+
"model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors",
|
| 78 |
+
"model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors",
|
| 79 |
+
"model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors",
|
| 80 |
+
"model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors",
|
| 81 |
+
"model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors",
|
| 82 |
+
"model.layers.10.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors",
|
| 83 |
+
"model.layers.10.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors",
|
| 84 |
+
"model.layers.10.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00019.safetensors",
|
| 85 |
+
"model.layers.10.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00019.safetensors",
|
| 86 |
+
"model.layers.10.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00019.safetensors",
|
| 87 |
+
"model.layers.10.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00019.safetensors",
|
| 88 |
+
"model.layers.10.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00019.safetensors",
|
| 89 |
+
"model.layers.10.block_sparse_moe.experts.6.w2.weight": "model-00007-of-00019.safetensors",
|
| 90 |
+
"model.layers.10.block_sparse_moe.experts.6.w3.weight": "model-00007-of-00019.safetensors",
|
| 91 |
+
"model.layers.10.block_sparse_moe.experts.7.w1.weight": "model-00007-of-00019.safetensors",
|
| 92 |
+
"model.layers.10.block_sparse_moe.experts.7.w2.weight": "model-00007-of-00019.safetensors",
|
| 93 |
+
"model.layers.10.block_sparse_moe.experts.7.w3.weight": "model-00007-of-00019.safetensors",
|
| 94 |
+
"model.layers.10.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors",
|
| 95 |
+
"model.layers.10.input_layernorm.weight": "model-00007-of-00019.safetensors",
|
| 96 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00007-of-00019.safetensors",
|
| 97 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00006-of-00019.safetensors",
|
| 98 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00006-of-00019.safetensors",
|
| 99 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00006-of-00019.safetensors",
|
| 100 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00006-of-00019.safetensors",
|
| 101 |
+
"model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00019.safetensors",
|
| 102 |
+
"model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00019.safetensors",
|
| 103 |
+
"model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00019.safetensors",
|
| 104 |
+
"model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00019.safetensors",
|
| 105 |
+
"model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00019.safetensors",
|
| 106 |
+
"model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00019.safetensors",
|
| 107 |
+
"model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00007-of-00019.safetensors",
|
| 108 |
+
"model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00007-of-00019.safetensors",
|
| 109 |
+
"model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00007-of-00019.safetensors",
|
| 110 |
+
"model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00007-of-00019.safetensors",
|
| 111 |
+
"model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00007-of-00019.safetensors",
|
| 112 |
+
"model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00007-of-00019.safetensors",
|
| 113 |
+
"model.layers.11.block_sparse_moe.experts.4.w1.weight": "model-00007-of-00019.safetensors",
|
| 114 |
+
"model.layers.11.block_sparse_moe.experts.4.w2.weight": "model-00007-of-00019.safetensors",
|
| 115 |
+
"model.layers.11.block_sparse_moe.experts.4.w3.weight": "model-00007-of-00019.safetensors",
|
| 116 |
+
"model.layers.11.block_sparse_moe.experts.5.w1.weight": "model-00007-of-00019.safetensors",
|
| 117 |
+
"model.layers.11.block_sparse_moe.experts.5.w2.weight": "model-00007-of-00019.safetensors",
|
| 118 |
+
"model.layers.11.block_sparse_moe.experts.5.w3.weight": "model-00007-of-00019.safetensors",
|
| 119 |
+
"model.layers.11.block_sparse_moe.experts.6.w1.weight": "model-00007-of-00019.safetensors",
|
| 120 |
+
"model.layers.11.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00019.safetensors",
|
| 121 |
+
"model.layers.11.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00019.safetensors",
|
| 122 |
+
"model.layers.11.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00019.safetensors",
|
| 123 |
+
"model.layers.11.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00019.safetensors",
|
| 124 |
+
"model.layers.11.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00019.safetensors",
|
| 125 |
+
"model.layers.11.block_sparse_moe.gate.weight": "model-00007-of-00019.safetensors",
|
| 126 |
+
"model.layers.11.input_layernorm.weight": "model-00008-of-00019.safetensors",
|
| 127 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00008-of-00019.safetensors",
|
| 128 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00007-of-00019.safetensors",
|
| 129 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00007-of-00019.safetensors",
|
| 130 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00007-of-00019.safetensors",
|
| 131 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00007-of-00019.safetensors",
|
| 132 |
+
"model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors",
|
| 133 |
+
"model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors",
|
| 134 |
+
"model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors",
|
| 135 |
+
"model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors",
|
| 136 |
+
"model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors",
|
| 137 |
+
"model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors",
|
| 138 |
+
"model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors",
|
| 139 |
+
"model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors",
|
| 140 |
+
"model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors",
|
| 141 |
+
"model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors",
|
| 142 |
+
"model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00019.safetensors",
|
| 143 |
+
"model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00019.safetensors",
|
| 144 |
+
"model.layers.12.block_sparse_moe.experts.4.w1.weight": "model-00008-of-00019.safetensors",
|
| 145 |
+
"model.layers.12.block_sparse_moe.experts.4.w2.weight": "model-00008-of-00019.safetensors",
|
| 146 |
+
"model.layers.12.block_sparse_moe.experts.4.w3.weight": "model-00008-of-00019.safetensors",
|
| 147 |
+
"model.layers.12.block_sparse_moe.experts.5.w1.weight": "model-00008-of-00019.safetensors",
|
| 148 |
+
"model.layers.12.block_sparse_moe.experts.5.w2.weight": "model-00008-of-00019.safetensors",
|
| 149 |
+
"model.layers.12.block_sparse_moe.experts.5.w3.weight": "model-00008-of-00019.safetensors",
|
| 150 |
+
"model.layers.12.block_sparse_moe.experts.6.w1.weight": "model-00008-of-00019.safetensors",
|
| 151 |
+
"model.layers.12.block_sparse_moe.experts.6.w2.weight": "model-00008-of-00019.safetensors",
|
| 152 |
+
"model.layers.12.block_sparse_moe.experts.6.w3.weight": "model-00008-of-00019.safetensors",
|
| 153 |
+
"model.layers.12.block_sparse_moe.experts.7.w1.weight": "model-00008-of-00019.safetensors",
|
| 154 |
+
"model.layers.12.block_sparse_moe.experts.7.w2.weight": "model-00008-of-00019.safetensors",
|
| 155 |
+
"model.layers.12.block_sparse_moe.experts.7.w3.weight": "model-00008-of-00019.safetensors",
|
| 156 |
+
"model.layers.12.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors",
|
| 157 |
+
"model.layers.12.input_layernorm.weight": "model-00008-of-00019.safetensors",
|
| 158 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00008-of-00019.safetensors",
|
| 159 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00008-of-00019.safetensors",
|
| 160 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00008-of-00019.safetensors",
|
| 161 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00008-of-00019.safetensors",
|
| 162 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00008-of-00019.safetensors",
|
| 163 |
+
"model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00019.safetensors",
|
| 164 |
+
"model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00019.safetensors",
|
| 165 |
+
"model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00019.safetensors",
|
| 166 |
+
"model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00019.safetensors",
|
| 167 |
+
"model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00019.safetensors",
|
| 168 |
+
"model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00019.safetensors",
|
| 169 |
+
"model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00008-of-00019.safetensors",
|
| 170 |
+
"model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00008-of-00019.safetensors",
|
| 171 |
+
"model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00008-of-00019.safetensors",
|
| 172 |
+
"model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00008-of-00019.safetensors",
|
| 173 |
+
"model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00008-of-00019.safetensors",
|
| 174 |
+
"model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00008-of-00019.safetensors",
|
| 175 |
+
"model.layers.13.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00019.safetensors",
|
| 176 |
+
"model.layers.13.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors",
|
| 177 |
+
"model.layers.13.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors",
|
| 178 |
+
"model.layers.13.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors",
|
| 179 |
+
"model.layers.13.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors",
|
| 180 |
+
"model.layers.13.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors",
|
| 181 |
+
"model.layers.13.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00019.safetensors",
|
| 182 |
+
"model.layers.13.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00019.safetensors",
|
| 183 |
+
"model.layers.13.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00019.safetensors",
|
| 184 |
+
"model.layers.13.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00019.safetensors",
|
| 185 |
+
"model.layers.13.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00019.safetensors",
|
| 186 |
+
"model.layers.13.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00019.safetensors",
|
| 187 |
+
"model.layers.13.block_sparse_moe.gate.weight": "model-00008-of-00019.safetensors",
|
| 188 |
+
"model.layers.13.input_layernorm.weight": "model-00009-of-00019.safetensors",
|
| 189 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00009-of-00019.safetensors",
|
| 190 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00008-of-00019.safetensors",
|
| 191 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00008-of-00019.safetensors",
|
| 192 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00008-of-00019.safetensors",
|
| 193 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00008-of-00019.safetensors",
|
| 194 |
+
"model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors",
|
| 195 |
+
"model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors",
|
| 196 |
+
"model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors",
|
| 197 |
+
"model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors",
|
| 198 |
+
"model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors",
|
| 199 |
+
"model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00019.safetensors",
|
| 200 |
+
"model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00009-of-00019.safetensors",
|
| 201 |
+
"model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00009-of-00019.safetensors",
|
| 202 |
+
"model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00009-of-00019.safetensors",
|
| 203 |
+
"model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00009-of-00019.safetensors",
|
| 204 |
+
"model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00009-of-00019.safetensors",
|
| 205 |
+
"model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00009-of-00019.safetensors",
|
| 206 |
+
"model.layers.14.block_sparse_moe.experts.4.w1.weight": "model-00009-of-00019.safetensors",
|
| 207 |
+
"model.layers.14.block_sparse_moe.experts.4.w2.weight": "model-00009-of-00019.safetensors",
|
| 208 |
+
"model.layers.14.block_sparse_moe.experts.4.w3.weight": "model-00009-of-00019.safetensors",
|
| 209 |
+
"model.layers.14.block_sparse_moe.experts.5.w1.weight": "model-00009-of-00019.safetensors",
|
| 210 |
+
"model.layers.14.block_sparse_moe.experts.5.w2.weight": "model-00009-of-00019.safetensors",
|
| 211 |
+
"model.layers.14.block_sparse_moe.experts.5.w3.weight": "model-00009-of-00019.safetensors",
|
| 212 |
+
"model.layers.14.block_sparse_moe.experts.6.w1.weight": "model-00009-of-00019.safetensors",
|
| 213 |
+
"model.layers.14.block_sparse_moe.experts.6.w2.weight": "model-00009-of-00019.safetensors",
|
| 214 |
+
"model.layers.14.block_sparse_moe.experts.6.w3.weight": "model-00009-of-00019.safetensors",
|
| 215 |
+
"model.layers.14.block_sparse_moe.experts.7.w1.weight": "model-00009-of-00019.safetensors",
|
| 216 |
+
"model.layers.14.block_sparse_moe.experts.7.w2.weight": "model-00009-of-00019.safetensors",
|
| 217 |
+
"model.layers.14.block_sparse_moe.experts.7.w3.weight": "model-00009-of-00019.safetensors",
|
| 218 |
+
"model.layers.14.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors",
|
| 219 |
+
"model.layers.14.input_layernorm.weight": "model-00009-of-00019.safetensors",
|
| 220 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00009-of-00019.safetensors",
|
| 221 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00009-of-00019.safetensors",
|
| 222 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00009-of-00019.safetensors",
|
| 223 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00009-of-00019.safetensors",
|
| 224 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00009-of-00019.safetensors",
|
| 225 |
+
"model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00019.safetensors",
|
| 226 |
+
"model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00019.safetensors",
|
| 227 |
+
"model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00019.safetensors",
|
| 228 |
+
"model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00019.safetensors",
|
| 229 |
+
"model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00019.safetensors",
|
| 230 |
+
"model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00019.safetensors",
|
| 231 |
+
"model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors",
|
| 232 |
+
"model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors",
|
| 233 |
+
"model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors",
|
| 234 |
+
"model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors",
|
| 235 |
+
"model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors",
|
| 236 |
+
"model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors",
|
| 237 |
+
"model.layers.15.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors",
|
| 238 |
+
"model.layers.15.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors",
|
| 239 |
+
"model.layers.15.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors",
|
| 240 |
+
"model.layers.15.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors",
|
| 241 |
+
"model.layers.15.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors",
|
| 242 |
+
"model.layers.15.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00019.safetensors",
|
| 243 |
+
"model.layers.15.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00019.safetensors",
|
| 244 |
+
"model.layers.15.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00019.safetensors",
|
| 245 |
+
"model.layers.15.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00019.safetensors",
|
| 246 |
+
"model.layers.15.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00019.safetensors",
|
| 247 |
+
"model.layers.15.block_sparse_moe.experts.7.w2.weight": "model-00010-of-00019.safetensors",
|
| 248 |
+
"model.layers.15.block_sparse_moe.experts.7.w3.weight": "model-00010-of-00019.safetensors",
|
| 249 |
+
"model.layers.15.block_sparse_moe.gate.weight": "model-00009-of-00019.safetensors",
|
| 250 |
+
"model.layers.15.input_layernorm.weight": "model-00010-of-00019.safetensors",
|
| 251 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00010-of-00019.safetensors",
|
| 252 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00009-of-00019.safetensors",
|
| 253 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00009-of-00019.safetensors",
|
| 254 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00009-of-00019.safetensors",
|
| 255 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00009-of-00019.safetensors",
|
| 256 |
+
"model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00019.safetensors",
|
| 257 |
+
"model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00019.safetensors",
|
| 258 |
+
"model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00019.safetensors",
|
| 259 |
+
"model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00019.safetensors",
|
| 260 |
+
"model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00019.safetensors",
|
| 261 |
+
"model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00019.safetensors",
|
| 262 |
+
"model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00010-of-00019.safetensors",
|
| 263 |
+
"model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00010-of-00019.safetensors",
|
| 264 |
+
"model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00010-of-00019.safetensors",
|
| 265 |
+
"model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00010-of-00019.safetensors",
|
| 266 |
+
"model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00010-of-00019.safetensors",
|
| 267 |
+
"model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00010-of-00019.safetensors",
|
| 268 |
+
"model.layers.16.block_sparse_moe.experts.4.w1.weight": "model-00010-of-00019.safetensors",
|
| 269 |
+
"model.layers.16.block_sparse_moe.experts.4.w2.weight": "model-00010-of-00019.safetensors",
|
| 270 |
+
"model.layers.16.block_sparse_moe.experts.4.w3.weight": "model-00010-of-00019.safetensors",
|
| 271 |
+
"model.layers.16.block_sparse_moe.experts.5.w1.weight": "model-00010-of-00019.safetensors",
|
| 272 |
+
"model.layers.16.block_sparse_moe.experts.5.w2.weight": "model-00010-of-00019.safetensors",
|
| 273 |
+
"model.layers.16.block_sparse_moe.experts.5.w3.weight": "model-00010-of-00019.safetensors",
|
| 274 |
+
"model.layers.16.block_sparse_moe.experts.6.w1.weight": "model-00010-of-00019.safetensors",
|
| 275 |
+
"model.layers.16.block_sparse_moe.experts.6.w2.weight": "model-00010-of-00019.safetensors",
|
| 276 |
+
"model.layers.16.block_sparse_moe.experts.6.w3.weight": "model-00010-of-00019.safetensors",
|
| 277 |
+
"model.layers.16.block_sparse_moe.experts.7.w1.weight": "model-00010-of-00019.safetensors",
|
| 278 |
+
"model.layers.16.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00019.safetensors",
|
| 279 |
+
"model.layers.16.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00019.safetensors",
|
| 280 |
+
"model.layers.16.block_sparse_moe.gate.weight": "model-00010-of-00019.safetensors",
|
| 281 |
+
"model.layers.16.input_layernorm.weight": "model-00011-of-00019.safetensors",
|
| 282 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00011-of-00019.safetensors",
|
| 283 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00010-of-00019.safetensors",
|
| 284 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00010-of-00019.safetensors",
|
| 285 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00010-of-00019.safetensors",
|
| 286 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00010-of-00019.safetensors",
|
| 287 |
+
"model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors",
|
| 288 |
+
"model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors",
|
| 289 |
+
"model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors",
|
| 290 |
+
"model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors",
|
| 291 |
+
"model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors",
|
| 292 |
+
"model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors",
|
| 293 |
+
"model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors",
|
| 294 |
+
"model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors",
|
| 295 |
+
"model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors",
|
| 296 |
+
"model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors",
|
| 297 |
+
"model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors",
|
| 298 |
+
"model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors",
|
| 299 |
+
"model.layers.17.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00019.safetensors",
|
| 300 |
+
"model.layers.17.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00019.safetensors",
|
| 301 |
+
"model.layers.17.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00019.safetensors",
|
| 302 |
+
"model.layers.17.block_sparse_moe.experts.5.w1.weight": "model-00011-of-00019.safetensors",
|
| 303 |
+
"model.layers.17.block_sparse_moe.experts.5.w2.weight": "model-00011-of-00019.safetensors",
|
| 304 |
+
"model.layers.17.block_sparse_moe.experts.5.w3.weight": "model-00011-of-00019.safetensors",
|
| 305 |
+
"model.layers.17.block_sparse_moe.experts.6.w1.weight": "model-00011-of-00019.safetensors",
|
| 306 |
+
"model.layers.17.block_sparse_moe.experts.6.w2.weight": "model-00011-of-00019.safetensors",
|
| 307 |
+
"model.layers.17.block_sparse_moe.experts.6.w3.weight": "model-00011-of-00019.safetensors",
|
| 308 |
+
"model.layers.17.block_sparse_moe.experts.7.w1.weight": "model-00011-of-00019.safetensors",
|
| 309 |
+
"model.layers.17.block_sparse_moe.experts.7.w2.weight": "model-00011-of-00019.safetensors",
|
| 310 |
+
"model.layers.17.block_sparse_moe.experts.7.w3.weight": "model-00011-of-00019.safetensors",
|
| 311 |
+
"model.layers.17.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors",
|
| 312 |
+
"model.layers.17.input_layernorm.weight": "model-00011-of-00019.safetensors",
|
| 313 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00011-of-00019.safetensors",
|
| 314 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00011-of-00019.safetensors",
|
| 315 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00011-of-00019.safetensors",
|
| 316 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00011-of-00019.safetensors",
|
| 317 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00011-of-00019.safetensors",
|
| 318 |
+
"model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00019.safetensors",
|
| 319 |
+
"model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00019.safetensors",
|
| 320 |
+
"model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00019.safetensors",
|
| 321 |
+
"model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00019.safetensors",
|
| 322 |
+
"model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00019.safetensors",
|
| 323 |
+
"model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00019.safetensors",
|
| 324 |
+
"model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00011-of-00019.safetensors",
|
| 325 |
+
"model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00011-of-00019.safetensors",
|
| 326 |
+
"model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00011-of-00019.safetensors",
|
| 327 |
+
"model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00011-of-00019.safetensors",
|
| 328 |
+
"model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00011-of-00019.safetensors",
|
| 329 |
+
"model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00011-of-00019.safetensors",
|
| 330 |
+
"model.layers.18.block_sparse_moe.experts.4.w1.weight": "model-00011-of-00019.safetensors",
|
| 331 |
+
"model.layers.18.block_sparse_moe.experts.4.w2.weight": "model-00011-of-00019.safetensors",
|
| 332 |
+
"model.layers.18.block_sparse_moe.experts.4.w3.weight": "model-00011-of-00019.safetensors",
|
| 333 |
+
"model.layers.18.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00019.safetensors",
|
| 334 |
+
"model.layers.18.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors",
|
| 335 |
+
"model.layers.18.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors",
|
| 336 |
+
"model.layers.18.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00019.safetensors",
|
| 337 |
+
"model.layers.18.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00019.safetensors",
|
| 338 |
+
"model.layers.18.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00019.safetensors",
|
| 339 |
+
"model.layers.18.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00019.safetensors",
|
| 340 |
+
"model.layers.18.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00019.safetensors",
|
| 341 |
+
"model.layers.18.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00019.safetensors",
|
| 342 |
+
"model.layers.18.block_sparse_moe.gate.weight": "model-00011-of-00019.safetensors",
|
| 343 |
+
"model.layers.18.input_layernorm.weight": "model-00012-of-00019.safetensors",
|
| 344 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00012-of-00019.safetensors",
|
| 345 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00011-of-00019.safetensors",
|
| 346 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00011-of-00019.safetensors",
|
| 347 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00011-of-00019.safetensors",
|
| 348 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00011-of-00019.safetensors",
|
| 349 |
+
"model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors",
|
| 350 |
+
"model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors",
|
| 351 |
+
"model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors",
|
| 352 |
+
"model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors",
|
| 353 |
+
"model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors",
|
| 354 |
+
"model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors",
|
| 355 |
+
"model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors",
|
| 356 |
+
"model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors",
|
| 357 |
+
"model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00012-of-00019.safetensors",
|
| 358 |
+
"model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00012-of-00019.safetensors",
|
| 359 |
+
"model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00012-of-00019.safetensors",
|
| 360 |
+
"model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00012-of-00019.safetensors",
|
| 361 |
+
"model.layers.19.block_sparse_moe.experts.4.w1.weight": "model-00012-of-00019.safetensors",
|
| 362 |
+
"model.layers.19.block_sparse_moe.experts.4.w2.weight": "model-00012-of-00019.safetensors",
|
| 363 |
+
"model.layers.19.block_sparse_moe.experts.4.w3.weight": "model-00012-of-00019.safetensors",
|
| 364 |
+
"model.layers.19.block_sparse_moe.experts.5.w1.weight": "model-00012-of-00019.safetensors",
|
| 365 |
+
"model.layers.19.block_sparse_moe.experts.5.w2.weight": "model-00012-of-00019.safetensors",
|
| 366 |
+
"model.layers.19.block_sparse_moe.experts.5.w3.weight": "model-00012-of-00019.safetensors",
|
| 367 |
+
"model.layers.19.block_sparse_moe.experts.6.w1.weight": "model-00012-of-00019.safetensors",
|
| 368 |
+
"model.layers.19.block_sparse_moe.experts.6.w2.weight": "model-00012-of-00019.safetensors",
|
| 369 |
+
"model.layers.19.block_sparse_moe.experts.6.w3.weight": "model-00012-of-00019.safetensors",
|
| 370 |
+
"model.layers.19.block_sparse_moe.experts.7.w1.weight": "model-00012-of-00019.safetensors",
|
| 371 |
+
"model.layers.19.block_sparse_moe.experts.7.w2.weight": "model-00012-of-00019.safetensors",
|
| 372 |
+
"model.layers.19.block_sparse_moe.experts.7.w3.weight": "model-00012-of-00019.safetensors",
|
| 373 |
+
"model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors",
|
| 374 |
+
"model.layers.19.input_layernorm.weight": "model-00012-of-00019.safetensors",
|
| 375 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00012-of-00019.safetensors",
|
| 376 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00012-of-00019.safetensors",
|
| 377 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00012-of-00019.safetensors",
|
| 378 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00012-of-00019.safetensors",
|
| 379 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00012-of-00019.safetensors",
|
| 380 |
+
"model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors",
|
| 381 |
+
"model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors",
|
| 382 |
+
"model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors",
|
| 383 |
+
"model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors",
|
| 384 |
+
"model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors",
|
| 385 |
+
"model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors",
|
| 386 |
+
"model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00019.safetensors",
|
| 387 |
+
"model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00019.safetensors",
|
| 388 |
+
"model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00019.safetensors",
|
| 389 |
+
"model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00019.safetensors",
|
| 390 |
+
"model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00019.safetensors",
|
| 391 |
+
"model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00019.safetensors",
|
| 392 |
+
"model.layers.2.block_sparse_moe.experts.4.w1.weight": "model-00002-of-00019.safetensors",
|
| 393 |
+
"model.layers.2.block_sparse_moe.experts.4.w2.weight": "model-00002-of-00019.safetensors",
|
| 394 |
+
"model.layers.2.block_sparse_moe.experts.4.w3.weight": "model-00002-of-00019.safetensors",
|
| 395 |
+
"model.layers.2.block_sparse_moe.experts.5.w1.weight": "model-00002-of-00019.safetensors",
|
| 396 |
+
"model.layers.2.block_sparse_moe.experts.5.w2.weight": "model-00002-of-00019.safetensors",
|
| 397 |
+
"model.layers.2.block_sparse_moe.experts.5.w3.weight": "model-00002-of-00019.safetensors",
|
| 398 |
+
"model.layers.2.block_sparse_moe.experts.6.w1.weight": "model-00002-of-00019.safetensors",
|
| 399 |
+
"model.layers.2.block_sparse_moe.experts.6.w2.weight": "model-00002-of-00019.safetensors",
|
| 400 |
+
"model.layers.2.block_sparse_moe.experts.6.w3.weight": "model-00002-of-00019.safetensors",
|
| 401 |
+
"model.layers.2.block_sparse_moe.experts.7.w1.weight": "model-00002-of-00019.safetensors",
|
| 402 |
+
"model.layers.2.block_sparse_moe.experts.7.w2.weight": "model-00002-of-00019.safetensors",
|
| 403 |
+
"model.layers.2.block_sparse_moe.experts.7.w3.weight": "model-00002-of-00019.safetensors",
|
| 404 |
+
"model.layers.2.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors",
|
| 405 |
+
"model.layers.2.input_layernorm.weight": "model-00002-of-00019.safetensors",
|
| 406 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00019.safetensors",
|
| 407 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00019.safetensors",
|
| 408 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00019.safetensors",
|
| 409 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00019.safetensors",
|
| 410 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00019.safetensors",
|
| 411 |
+
"model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00012-of-00019.safetensors",
|
| 412 |
+
"model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00012-of-00019.safetensors",
|
| 413 |
+
"model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00012-of-00019.safetensors",
|
| 414 |
+
"model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00012-of-00019.safetensors",
|
| 415 |
+
"model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00012-of-00019.safetensors",
|
| 416 |
+
"model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00012-of-00019.safetensors",
|
| 417 |
+
"model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00012-of-00019.safetensors",
|
| 418 |
+
"model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00012-of-00019.safetensors",
|
| 419 |
+
"model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00019.safetensors",
|
| 420 |
+
"model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors",
|
| 421 |
+
"model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors",
|
| 422 |
+
"model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors",
|
| 423 |
+
"model.layers.20.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors",
|
| 424 |
+
"model.layers.20.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors",
|
| 425 |
+
"model.layers.20.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors",
|
| 426 |
+
"model.layers.20.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors",
|
| 427 |
+
"model.layers.20.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors",
|
| 428 |
+
"model.layers.20.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors",
|
| 429 |
+
"model.layers.20.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00019.safetensors",
|
| 430 |
+
"model.layers.20.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00019.safetensors",
|
| 431 |
+
"model.layers.20.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00019.safetensors",
|
| 432 |
+
"model.layers.20.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00019.safetensors",
|
| 433 |
+
"model.layers.20.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00019.safetensors",
|
| 434 |
+
"model.layers.20.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00019.safetensors",
|
| 435 |
+
"model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00019.safetensors",
|
| 436 |
+
"model.layers.20.input_layernorm.weight": "model-00013-of-00019.safetensors",
|
| 437 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00013-of-00019.safetensors",
|
| 438 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00012-of-00019.safetensors",
|
| 439 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00012-of-00019.safetensors",
|
| 440 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00012-of-00019.safetensors",
|
| 441 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00012-of-00019.safetensors",
|
| 442 |
+
"model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors",
|
| 443 |
+
"model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00013-of-00019.safetensors",
|
| 444 |
+
"model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00013-of-00019.safetensors",
|
| 445 |
+
"model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00013-of-00019.safetensors",
|
| 446 |
+
"model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00013-of-00019.safetensors",
|
| 447 |
+
"model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00013-of-00019.safetensors",
|
| 448 |
+
"model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00013-of-00019.safetensors",
|
| 449 |
+
"model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00013-of-00019.safetensors",
|
| 450 |
+
"model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00013-of-00019.safetensors",
|
| 451 |
+
"model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00013-of-00019.safetensors",
|
| 452 |
+
"model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00013-of-00019.safetensors",
|
| 453 |
+
"model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00013-of-00019.safetensors",
|
| 454 |
+
"model.layers.21.block_sparse_moe.experts.4.w1.weight": "model-00013-of-00019.safetensors",
|
| 455 |
+
"model.layers.21.block_sparse_moe.experts.4.w2.weight": "model-00013-of-00019.safetensors",
|
| 456 |
+
"model.layers.21.block_sparse_moe.experts.4.w3.weight": "model-00013-of-00019.safetensors",
|
| 457 |
+
"model.layers.21.block_sparse_moe.experts.5.w1.weight": "model-00013-of-00019.safetensors",
|
| 458 |
+
"model.layers.21.block_sparse_moe.experts.5.w2.weight": "model-00013-of-00019.safetensors",
|
| 459 |
+
"model.layers.21.block_sparse_moe.experts.5.w3.weight": "model-00013-of-00019.safetensors",
|
| 460 |
+
"model.layers.21.block_sparse_moe.experts.6.w1.weight": "model-00013-of-00019.safetensors",
|
| 461 |
+
"model.layers.21.block_sparse_moe.experts.6.w2.weight": "model-00013-of-00019.safetensors",
|
| 462 |
+
"model.layers.21.block_sparse_moe.experts.6.w3.weight": "model-00013-of-00019.safetensors",
|
| 463 |
+
"model.layers.21.block_sparse_moe.experts.7.w1.weight": "model-00013-of-00019.safetensors",
|
| 464 |
+
"model.layers.21.block_sparse_moe.experts.7.w2.weight": "model-00013-of-00019.safetensors",
|
| 465 |
+
"model.layers.21.block_sparse_moe.experts.7.w3.weight": "model-00013-of-00019.safetensors",
|
| 466 |
+
"model.layers.21.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors",
|
| 467 |
+
"model.layers.21.input_layernorm.weight": "model-00013-of-00019.safetensors",
|
| 468 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00013-of-00019.safetensors",
|
| 469 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00013-of-00019.safetensors",
|
| 470 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00013-of-00019.safetensors",
|
| 471 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00013-of-00019.safetensors",
|
| 472 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00013-of-00019.safetensors",
|
| 473 |
+
"model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00013-of-00019.safetensors",
|
| 474 |
+
"model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00019.safetensors",
|
| 475 |
+
"model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors",
|
| 476 |
+
"model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors",
|
| 477 |
+
"model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors",
|
| 478 |
+
"model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors",
|
| 479 |
+
"model.layers.22.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors",
|
| 480 |
+
"model.layers.22.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors",
|
| 481 |
+
"model.layers.22.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors",
|
| 482 |
+
"model.layers.22.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors",
|
| 483 |
+
"model.layers.22.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors",
|
| 484 |
+
"model.layers.22.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors",
|
| 485 |
+
"model.layers.22.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors",
|
| 486 |
+
"model.layers.22.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00019.safetensors",
|
| 487 |
+
"model.layers.22.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00019.safetensors",
|
| 488 |
+
"model.layers.22.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00019.safetensors",
|
| 489 |
+
"model.layers.22.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00019.safetensors",
|
| 490 |
+
"model.layers.22.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00019.safetensors",
|
| 491 |
+
"model.layers.22.block_sparse_moe.experts.6.w1.weight": "model-00014-of-00019.safetensors",
|
| 492 |
+
"model.layers.22.block_sparse_moe.experts.6.w2.weight": "model-00014-of-00019.safetensors",
|
| 493 |
+
"model.layers.22.block_sparse_moe.experts.6.w3.weight": "model-00014-of-00019.safetensors",
|
| 494 |
+
"model.layers.22.block_sparse_moe.experts.7.w1.weight": "model-00014-of-00019.safetensors",
|
| 495 |
+
"model.layers.22.block_sparse_moe.experts.7.w2.weight": "model-00014-of-00019.safetensors",
|
| 496 |
+
"model.layers.22.block_sparse_moe.experts.7.w3.weight": "model-00014-of-00019.safetensors",
|
| 497 |
+
"model.layers.22.block_sparse_moe.gate.weight": "model-00013-of-00019.safetensors",
|
| 498 |
+
"model.layers.22.input_layernorm.weight": "model-00014-of-00019.safetensors",
|
| 499 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00014-of-00019.safetensors",
|
| 500 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00013-of-00019.safetensors",
|
| 501 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00013-of-00019.safetensors",
|
| 502 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00013-of-00019.safetensors",
|
| 503 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00013-of-00019.safetensors",
|
| 504 |
+
"model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00014-of-00019.safetensors",
|
| 505 |
+
"model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00014-of-00019.safetensors",
|
| 506 |
+
"model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00014-of-00019.safetensors",
|
| 507 |
+
"model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00014-of-00019.safetensors",
|
| 508 |
+
"model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00014-of-00019.safetensors",
|
| 509 |
+
"model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00014-of-00019.safetensors",
|
| 510 |
+
"model.layers.23.block_sparse_moe.experts.2.w1.weight": "model-00014-of-00019.safetensors",
|
| 511 |
+
"model.layers.23.block_sparse_moe.experts.2.w2.weight": "model-00014-of-00019.safetensors",
|
| 512 |
+
"model.layers.23.block_sparse_moe.experts.2.w3.weight": "model-00014-of-00019.safetensors",
|
| 513 |
+
"model.layers.23.block_sparse_moe.experts.3.w1.weight": "model-00014-of-00019.safetensors",
|
| 514 |
+
"model.layers.23.block_sparse_moe.experts.3.w2.weight": "model-00014-of-00019.safetensors",
|
| 515 |
+
"model.layers.23.block_sparse_moe.experts.3.w3.weight": "model-00014-of-00019.safetensors",
|
| 516 |
+
"model.layers.23.block_sparse_moe.experts.4.w1.weight": "model-00014-of-00019.safetensors",
|
| 517 |
+
"model.layers.23.block_sparse_moe.experts.4.w2.weight": "model-00014-of-00019.safetensors",
|
| 518 |
+
"model.layers.23.block_sparse_moe.experts.4.w3.weight": "model-00014-of-00019.safetensors",
|
| 519 |
+
"model.layers.23.block_sparse_moe.experts.5.w1.weight": "model-00014-of-00019.safetensors",
|
| 520 |
+
"model.layers.23.block_sparse_moe.experts.5.w2.weight": "model-00014-of-00019.safetensors",
|
| 521 |
+
"model.layers.23.block_sparse_moe.experts.5.w3.weight": "model-00014-of-00019.safetensors",
|
| 522 |
+
"model.layers.23.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00019.safetensors",
|
| 523 |
+
"model.layers.23.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00019.safetensors",
|
| 524 |
+
"model.layers.23.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00019.safetensors",
|
| 525 |
+
"model.layers.23.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00019.safetensors",
|
| 526 |
+
"model.layers.23.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00019.safetensors",
|
| 527 |
+
"model.layers.23.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00019.safetensors",
|
| 528 |
+
"model.layers.23.block_sparse_moe.gate.weight": "model-00014-of-00019.safetensors",
|
| 529 |
+
"model.layers.23.input_layernorm.weight": "model-00015-of-00019.safetensors",
|
| 530 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00015-of-00019.safetensors",
|
| 531 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00014-of-00019.safetensors",
|
| 532 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00014-of-00019.safetensors",
|
| 533 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00014-of-00019.safetensors",
|
| 534 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00014-of-00019.safetensors",
|
| 535 |
+
"model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors",
|
| 536 |
+
"model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors",
|
| 537 |
+
"model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors",
|
| 538 |
+
"model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors",
|
| 539 |
+
"model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors",
|
| 540 |
+
"model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors",
|
| 541 |
+
"model.layers.24.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors",
|
| 542 |
+
"model.layers.24.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors",
|
| 543 |
+
"model.layers.24.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors",
|
| 544 |
+
"model.layers.24.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00019.safetensors",
|
| 545 |
+
"model.layers.24.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00019.safetensors",
|
| 546 |
+
"model.layers.24.block_sparse_moe.experts.3.w3.weight": "model-00015-of-00019.safetensors",
|
| 547 |
+
"model.layers.24.block_sparse_moe.experts.4.w1.weight": "model-00015-of-00019.safetensors",
|
| 548 |
+
"model.layers.24.block_sparse_moe.experts.4.w2.weight": "model-00015-of-00019.safetensors",
|
| 549 |
+
"model.layers.24.block_sparse_moe.experts.4.w3.weight": "model-00015-of-00019.safetensors",
|
| 550 |
+
"model.layers.24.block_sparse_moe.experts.5.w1.weight": "model-00015-of-00019.safetensors",
|
| 551 |
+
"model.layers.24.block_sparse_moe.experts.5.w2.weight": "model-00015-of-00019.safetensors",
|
| 552 |
+
"model.layers.24.block_sparse_moe.experts.5.w3.weight": "model-00015-of-00019.safetensors",
|
| 553 |
+
"model.layers.24.block_sparse_moe.experts.6.w1.weight": "model-00015-of-00019.safetensors",
|
| 554 |
+
"model.layers.24.block_sparse_moe.experts.6.w2.weight": "model-00015-of-00019.safetensors",
|
| 555 |
+
"model.layers.24.block_sparse_moe.experts.6.w3.weight": "model-00015-of-00019.safetensors",
|
| 556 |
+
"model.layers.24.block_sparse_moe.experts.7.w1.weight": "model-00015-of-00019.safetensors",
|
| 557 |
+
"model.layers.24.block_sparse_moe.experts.7.w2.weight": "model-00015-of-00019.safetensors",
|
| 558 |
+
"model.layers.24.block_sparse_moe.experts.7.w3.weight": "model-00015-of-00019.safetensors",
|
| 559 |
+
"model.layers.24.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors",
|
| 560 |
+
"model.layers.24.input_layernorm.weight": "model-00015-of-00019.safetensors",
|
| 561 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00015-of-00019.safetensors",
|
| 562 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00015-of-00019.safetensors",
|
| 563 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00015-of-00019.safetensors",
|
| 564 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00015-of-00019.safetensors",
|
| 565 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00015-of-00019.safetensors",
|
| 566 |
+
"model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00015-of-00019.safetensors",
|
| 567 |
+
"model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00015-of-00019.safetensors",
|
| 568 |
+
"model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00015-of-00019.safetensors",
|
| 569 |
+
"model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00015-of-00019.safetensors",
|
| 570 |
+
"model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00015-of-00019.safetensors",
|
| 571 |
+
"model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00015-of-00019.safetensors",
|
| 572 |
+
"model.layers.25.block_sparse_moe.experts.2.w1.weight": "model-00015-of-00019.safetensors",
|
| 573 |
+
"model.layers.25.block_sparse_moe.experts.2.w2.weight": "model-00015-of-00019.safetensors",
|
| 574 |
+
"model.layers.25.block_sparse_moe.experts.2.w3.weight": "model-00015-of-00019.safetensors",
|
| 575 |
+
"model.layers.25.block_sparse_moe.experts.3.w1.weight": "model-00015-of-00019.safetensors",
|
| 576 |
+
"model.layers.25.block_sparse_moe.experts.3.w2.weight": "model-00015-of-00019.safetensors",
|
| 577 |
+
"model.layers.25.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00019.safetensors",
|
| 578 |
+
"model.layers.25.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors",
|
| 579 |
+
"model.layers.25.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors",
|
| 580 |
+
"model.layers.25.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors",
|
| 581 |
+
"model.layers.25.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors",
|
| 582 |
+
"model.layers.25.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors",
|
| 583 |
+
"model.layers.25.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors",
|
| 584 |
+
"model.layers.25.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00019.safetensors",
|
| 585 |
+
"model.layers.25.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00019.safetensors",
|
| 586 |
+
"model.layers.25.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00019.safetensors",
|
| 587 |
+
"model.layers.25.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00019.safetensors",
|
| 588 |
+
"model.layers.25.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00019.safetensors",
|
| 589 |
+
"model.layers.25.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00019.safetensors",
|
| 590 |
+
"model.layers.25.block_sparse_moe.gate.weight": "model-00015-of-00019.safetensors",
|
| 591 |
+
"model.layers.25.input_layernorm.weight": "model-00016-of-00019.safetensors",
|
| 592 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00016-of-00019.safetensors",
|
| 593 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00015-of-00019.safetensors",
|
| 594 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00015-of-00019.safetensors",
|
| 595 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00015-of-00019.safetensors",
|
| 596 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00015-of-00019.safetensors",
|
| 597 |
+
"model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors",
|
| 598 |
+
"model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors",
|
| 599 |
+
"model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors",
|
| 600 |
+
"model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors",
|
| 601 |
+
"model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00016-of-00019.safetensors",
|
| 602 |
+
"model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00016-of-00019.safetensors",
|
| 603 |
+
"model.layers.26.block_sparse_moe.experts.2.w1.weight": "model-00016-of-00019.safetensors",
|
| 604 |
+
"model.layers.26.block_sparse_moe.experts.2.w2.weight": "model-00016-of-00019.safetensors",
|
| 605 |
+
"model.layers.26.block_sparse_moe.experts.2.w3.weight": "model-00016-of-00019.safetensors",
|
| 606 |
+
"model.layers.26.block_sparse_moe.experts.3.w1.weight": "model-00016-of-00019.safetensors",
|
| 607 |
+
"model.layers.26.block_sparse_moe.experts.3.w2.weight": "model-00016-of-00019.safetensors",
|
| 608 |
+
"model.layers.26.block_sparse_moe.experts.3.w3.weight": "model-00016-of-00019.safetensors",
|
| 609 |
+
"model.layers.26.block_sparse_moe.experts.4.w1.weight": "model-00016-of-00019.safetensors",
|
| 610 |
+
"model.layers.26.block_sparse_moe.experts.4.w2.weight": "model-00016-of-00019.safetensors",
|
| 611 |
+
"model.layers.26.block_sparse_moe.experts.4.w3.weight": "model-00016-of-00019.safetensors",
|
| 612 |
+
"model.layers.26.block_sparse_moe.experts.5.w1.weight": "model-00016-of-00019.safetensors",
|
| 613 |
+
"model.layers.26.block_sparse_moe.experts.5.w2.weight": "model-00016-of-00019.safetensors",
|
| 614 |
+
"model.layers.26.block_sparse_moe.experts.5.w3.weight": "model-00016-of-00019.safetensors",
|
| 615 |
+
"model.layers.26.block_sparse_moe.experts.6.w1.weight": "model-00016-of-00019.safetensors",
|
| 616 |
+
"model.layers.26.block_sparse_moe.experts.6.w2.weight": "model-00016-of-00019.safetensors",
|
| 617 |
+
"model.layers.26.block_sparse_moe.experts.6.w3.weight": "model-00016-of-00019.safetensors",
|
| 618 |
+
"model.layers.26.block_sparse_moe.experts.7.w1.weight": "model-00016-of-00019.safetensors",
|
| 619 |
+
"model.layers.26.block_sparse_moe.experts.7.w2.weight": "model-00016-of-00019.safetensors",
|
| 620 |
+
"model.layers.26.block_sparse_moe.experts.7.w3.weight": "model-00016-of-00019.safetensors",
|
| 621 |
+
"model.layers.26.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors",
|
| 622 |
+
"model.layers.26.input_layernorm.weight": "model-00016-of-00019.safetensors",
|
| 623 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00016-of-00019.safetensors",
|
| 624 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00016-of-00019.safetensors",
|
| 625 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00016-of-00019.safetensors",
|
| 626 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00016-of-00019.safetensors",
|
| 627 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00016-of-00019.safetensors",
|
| 628 |
+
"model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00016-of-00019.safetensors",
|
| 629 |
+
"model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00016-of-00019.safetensors",
|
| 630 |
+
"model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00016-of-00019.safetensors",
|
| 631 |
+
"model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00016-of-00019.safetensors",
|
| 632 |
+
"model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00019.safetensors",
|
| 633 |
+
"model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors",
|
| 634 |
+
"model.layers.27.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors",
|
| 635 |
+
"model.layers.27.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors",
|
| 636 |
+
"model.layers.27.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors",
|
| 637 |
+
"model.layers.27.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors",
|
| 638 |
+
"model.layers.27.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors",
|
| 639 |
+
"model.layers.27.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors",
|
| 640 |
+
"model.layers.27.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors",
|
| 641 |
+
"model.layers.27.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors",
|
| 642 |
+
"model.layers.27.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors",
|
| 643 |
+
"model.layers.27.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors",
|
| 644 |
+
"model.layers.27.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00019.safetensors",
|
| 645 |
+
"model.layers.27.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00019.safetensors",
|
| 646 |
+
"model.layers.27.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00019.safetensors",
|
| 647 |
+
"model.layers.27.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00019.safetensors",
|
| 648 |
+
"model.layers.27.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00019.safetensors",
|
| 649 |
+
"model.layers.27.block_sparse_moe.experts.7.w1.weight": "model-00017-of-00019.safetensors",
|
| 650 |
+
"model.layers.27.block_sparse_moe.experts.7.w2.weight": "model-00017-of-00019.safetensors",
|
| 651 |
+
"model.layers.27.block_sparse_moe.experts.7.w3.weight": "model-00017-of-00019.safetensors",
|
| 652 |
+
"model.layers.27.block_sparse_moe.gate.weight": "model-00016-of-00019.safetensors",
|
| 653 |
+
"model.layers.27.input_layernorm.weight": "model-00017-of-00019.safetensors",
|
| 654 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00017-of-00019.safetensors",
|
| 655 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00016-of-00019.safetensors",
|
| 656 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00016-of-00019.safetensors",
|
| 657 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00016-of-00019.safetensors",
|
| 658 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00016-of-00019.safetensors",
|
| 659 |
+
"model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00017-of-00019.safetensors",
|
| 660 |
+
"model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00017-of-00019.safetensors",
|
| 661 |
+
"model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00017-of-00019.safetensors",
|
| 662 |
+
"model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00017-of-00019.safetensors",
|
| 663 |
+
"model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00017-of-00019.safetensors",
|
| 664 |
+
"model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00017-of-00019.safetensors",
|
| 665 |
+
"model.layers.28.block_sparse_moe.experts.2.w1.weight": "model-00017-of-00019.safetensors",
|
| 666 |
+
"model.layers.28.block_sparse_moe.experts.2.w2.weight": "model-00017-of-00019.safetensors",
|
| 667 |
+
"model.layers.28.block_sparse_moe.experts.2.w3.weight": "model-00017-of-00019.safetensors",
|
| 668 |
+
"model.layers.28.block_sparse_moe.experts.3.w1.weight": "model-00017-of-00019.safetensors",
|
| 669 |
+
"model.layers.28.block_sparse_moe.experts.3.w2.weight": "model-00017-of-00019.safetensors",
|
| 670 |
+
"model.layers.28.block_sparse_moe.experts.3.w3.weight": "model-00017-of-00019.safetensors",
|
| 671 |
+
"model.layers.28.block_sparse_moe.experts.4.w1.weight": "model-00017-of-00019.safetensors",
|
| 672 |
+
"model.layers.28.block_sparse_moe.experts.4.w2.weight": "model-00017-of-00019.safetensors",
|
| 673 |
+
"model.layers.28.block_sparse_moe.experts.4.w3.weight": "model-00017-of-00019.safetensors",
|
| 674 |
+
"model.layers.28.block_sparse_moe.experts.5.w1.weight": "model-00017-of-00019.safetensors",
|
| 675 |
+
"model.layers.28.block_sparse_moe.experts.5.w2.weight": "model-00017-of-00019.safetensors",
|
| 676 |
+
"model.layers.28.block_sparse_moe.experts.5.w3.weight": "model-00017-of-00019.safetensors",
|
| 677 |
+
"model.layers.28.block_sparse_moe.experts.6.w1.weight": "model-00017-of-00019.safetensors",
|
| 678 |
+
"model.layers.28.block_sparse_moe.experts.6.w2.weight": "model-00017-of-00019.safetensors",
|
| 679 |
+
"model.layers.28.block_sparse_moe.experts.6.w3.weight": "model-00017-of-00019.safetensors",
|
| 680 |
+
"model.layers.28.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00019.safetensors",
|
| 681 |
+
"model.layers.28.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00019.safetensors",
|
| 682 |
+
"model.layers.28.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00019.safetensors",
|
| 683 |
+
"model.layers.28.block_sparse_moe.gate.weight": "model-00017-of-00019.safetensors",
|
| 684 |
+
"model.layers.28.input_layernorm.weight": "model-00018-of-00019.safetensors",
|
| 685 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00018-of-00019.safetensors",
|
| 686 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00017-of-00019.safetensors",
|
| 687 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00017-of-00019.safetensors",
|
| 688 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00017-of-00019.safetensors",
|
| 689 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00017-of-00019.safetensors",
|
| 690 |
+
"model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors",
|
| 691 |
+
"model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors",
|
| 692 |
+
"model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors",
|
| 693 |
+
"model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors",
|
| 694 |
+
"model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors",
|
| 695 |
+
"model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors",
|
| 696 |
+
"model.layers.29.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors",
|
| 697 |
+
"model.layers.29.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors",
|
| 698 |
+
"model.layers.29.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors",
|
| 699 |
+
"model.layers.29.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors",
|
| 700 |
+
"model.layers.29.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors",
|
| 701 |
+
"model.layers.29.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors",
|
| 702 |
+
"model.layers.29.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00019.safetensors",
|
| 703 |
+
"model.layers.29.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00019.safetensors",
|
| 704 |
+
"model.layers.29.block_sparse_moe.experts.4.w3.weight": "model-00018-of-00019.safetensors",
|
| 705 |
+
"model.layers.29.block_sparse_moe.experts.5.w1.weight": "model-00018-of-00019.safetensors",
|
| 706 |
+
"model.layers.29.block_sparse_moe.experts.5.w2.weight": "model-00018-of-00019.safetensors",
|
| 707 |
+
"model.layers.29.block_sparse_moe.experts.5.w3.weight": "model-00018-of-00019.safetensors",
|
| 708 |
+
"model.layers.29.block_sparse_moe.experts.6.w1.weight": "model-00018-of-00019.safetensors",
|
| 709 |
+
"model.layers.29.block_sparse_moe.experts.6.w2.weight": "model-00018-of-00019.safetensors",
|
| 710 |
+
"model.layers.29.block_sparse_moe.experts.6.w3.weight": "model-00018-of-00019.safetensors",
|
| 711 |
+
"model.layers.29.block_sparse_moe.experts.7.w1.weight": "model-00018-of-00019.safetensors",
|
| 712 |
+
"model.layers.29.block_sparse_moe.experts.7.w2.weight": "model-00018-of-00019.safetensors",
|
| 713 |
+
"model.layers.29.block_sparse_moe.experts.7.w3.weight": "model-00018-of-00019.safetensors",
|
| 714 |
+
"model.layers.29.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors",
|
| 715 |
+
"model.layers.29.input_layernorm.weight": "model-00018-of-00019.safetensors",
|
| 716 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00018-of-00019.safetensors",
|
| 717 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00018-of-00019.safetensors",
|
| 718 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00018-of-00019.safetensors",
|
| 719 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00018-of-00019.safetensors",
|
| 720 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00018-of-00019.safetensors",
|
| 721 |
+
"model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00019.safetensors",
|
| 722 |
+
"model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00019.safetensors",
|
| 723 |
+
"model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00019.safetensors",
|
| 724 |
+
"model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00019.safetensors",
|
| 725 |
+
"model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00019.safetensors",
|
| 726 |
+
"model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00019.safetensors",
|
| 727 |
+
"model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00019.safetensors",
|
| 728 |
+
"model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors",
|
| 729 |
+
"model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors",
|
| 730 |
+
"model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors",
|
| 731 |
+
"model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors",
|
| 732 |
+
"model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors",
|
| 733 |
+
"model.layers.3.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors",
|
| 734 |
+
"model.layers.3.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors",
|
| 735 |
+
"model.layers.3.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors",
|
| 736 |
+
"model.layers.3.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors",
|
| 737 |
+
"model.layers.3.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors",
|
| 738 |
+
"model.layers.3.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors",
|
| 739 |
+
"model.layers.3.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00019.safetensors",
|
| 740 |
+
"model.layers.3.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00019.safetensors",
|
| 741 |
+
"model.layers.3.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00019.safetensors",
|
| 742 |
+
"model.layers.3.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00019.safetensors",
|
| 743 |
+
"model.layers.3.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00019.safetensors",
|
| 744 |
+
"model.layers.3.block_sparse_moe.experts.7.w3.weight": "model-00003-of-00019.safetensors",
|
| 745 |
+
"model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00019.safetensors",
|
| 746 |
+
"model.layers.3.input_layernorm.weight": "model-00003-of-00019.safetensors",
|
| 747 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00019.safetensors",
|
| 748 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00019.safetensors",
|
| 749 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00019.safetensors",
|
| 750 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00019.safetensors",
|
| 751 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00019.safetensors",
|
| 752 |
+
"model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00018-of-00019.safetensors",
|
| 753 |
+
"model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00018-of-00019.safetensors",
|
| 754 |
+
"model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00018-of-00019.safetensors",
|
| 755 |
+
"model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00018-of-00019.safetensors",
|
| 756 |
+
"model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00018-of-00019.safetensors",
|
| 757 |
+
"model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00018-of-00019.safetensors",
|
| 758 |
+
"model.layers.30.block_sparse_moe.experts.2.w1.weight": "model-00018-of-00019.safetensors",
|
| 759 |
+
"model.layers.30.block_sparse_moe.experts.2.w2.weight": "model-00018-of-00019.safetensors",
|
| 760 |
+
"model.layers.30.block_sparse_moe.experts.2.w3.weight": "model-00018-of-00019.safetensors",
|
| 761 |
+
"model.layers.30.block_sparse_moe.experts.3.w1.weight": "model-00018-of-00019.safetensors",
|
| 762 |
+
"model.layers.30.block_sparse_moe.experts.3.w2.weight": "model-00018-of-00019.safetensors",
|
| 763 |
+
"model.layers.30.block_sparse_moe.experts.3.w3.weight": "model-00018-of-00019.safetensors",
|
| 764 |
+
"model.layers.30.block_sparse_moe.experts.4.w1.weight": "model-00018-of-00019.safetensors",
|
| 765 |
+
"model.layers.30.block_sparse_moe.experts.4.w2.weight": "model-00018-of-00019.safetensors",
|
| 766 |
+
"model.layers.30.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00019.safetensors",
|
| 767 |
+
"model.layers.30.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors",
|
| 768 |
+
"model.layers.30.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors",
|
| 769 |
+
"model.layers.30.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors",
|
| 770 |
+
"model.layers.30.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00019.safetensors",
|
| 771 |
+
"model.layers.30.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00019.safetensors",
|
| 772 |
+
"model.layers.30.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00019.safetensors",
|
| 773 |
+
"model.layers.30.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00019.safetensors",
|
| 774 |
+
"model.layers.30.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00019.safetensors",
|
| 775 |
+
"model.layers.30.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00019.safetensors",
|
| 776 |
+
"model.layers.30.block_sparse_moe.gate.weight": "model-00018-of-00019.safetensors",
|
| 777 |
+
"model.layers.30.input_layernorm.weight": "model-00019-of-00019.safetensors",
|
| 778 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
|
| 779 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00018-of-00019.safetensors",
|
| 780 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00018-of-00019.safetensors",
|
| 781 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00018-of-00019.safetensors",
|
| 782 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00018-of-00019.safetensors",
|
| 783 |
+
"model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00019-of-00019.safetensors",
|
| 784 |
+
"model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00019-of-00019.safetensors",
|
| 785 |
+
"model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00019-of-00019.safetensors",
|
| 786 |
+
"model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00019-of-00019.safetensors",
|
| 787 |
+
"model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00019-of-00019.safetensors",
|
| 788 |
+
"model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00019-of-00019.safetensors",
|
| 789 |
+
"model.layers.31.block_sparse_moe.experts.2.w1.weight": "model-00019-of-00019.safetensors",
|
| 790 |
+
"model.layers.31.block_sparse_moe.experts.2.w2.weight": "model-00019-of-00019.safetensors",
|
| 791 |
+
"model.layers.31.block_sparse_moe.experts.2.w3.weight": "model-00019-of-00019.safetensors",
|
| 792 |
+
"model.layers.31.block_sparse_moe.experts.3.w1.weight": "model-00019-of-00019.safetensors",
|
| 793 |
+
"model.layers.31.block_sparse_moe.experts.3.w2.weight": "model-00019-of-00019.safetensors",
|
| 794 |
+
"model.layers.31.block_sparse_moe.experts.3.w3.weight": "model-00019-of-00019.safetensors",
|
| 795 |
+
"model.layers.31.block_sparse_moe.experts.4.w1.weight": "model-00019-of-00019.safetensors",
|
| 796 |
+
"model.layers.31.block_sparse_moe.experts.4.w2.weight": "model-00019-of-00019.safetensors",
|
| 797 |
+
"model.layers.31.block_sparse_moe.experts.4.w3.weight": "model-00019-of-00019.safetensors",
|
| 798 |
+
"model.layers.31.block_sparse_moe.experts.5.w1.weight": "model-00019-of-00019.safetensors",
|
| 799 |
+
"model.layers.31.block_sparse_moe.experts.5.w2.weight": "model-00019-of-00019.safetensors",
|
| 800 |
+
"model.layers.31.block_sparse_moe.experts.5.w3.weight": "model-00019-of-00019.safetensors",
|
| 801 |
+
"model.layers.31.block_sparse_moe.experts.6.w1.weight": "model-00019-of-00019.safetensors",
|
| 802 |
+
"model.layers.31.block_sparse_moe.experts.6.w2.weight": "model-00019-of-00019.safetensors",
|
| 803 |
+
"model.layers.31.block_sparse_moe.experts.6.w3.weight": "model-00019-of-00019.safetensors",
|
| 804 |
+
"model.layers.31.block_sparse_moe.experts.7.w1.weight": "model-00019-of-00019.safetensors",
|
| 805 |
+
"model.layers.31.block_sparse_moe.experts.7.w2.weight": "model-00019-of-00019.safetensors",
|
| 806 |
+
"model.layers.31.block_sparse_moe.experts.7.w3.weight": "model-00019-of-00019.safetensors",
|
| 807 |
+
"model.layers.31.block_sparse_moe.gate.weight": "model-00019-of-00019.safetensors",
|
| 808 |
+
"model.layers.31.input_layernorm.weight": "model-00019-of-00019.safetensors",
|
| 809 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00019-of-00019.safetensors",
|
| 810 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00019-of-00019.safetensors",
|
| 811 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00019-of-00019.safetensors",
|
| 812 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00019-of-00019.safetensors",
|
| 813 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00019-of-00019.safetensors",
|
| 814 |
+
"model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00019.safetensors",
|
| 815 |
+
"model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00019.safetensors",
|
| 816 |
+
"model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00019.safetensors",
|
| 817 |
+
"model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00019.safetensors",
|
| 818 |
+
"model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00019.safetensors",
|
| 819 |
+
"model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00019.safetensors",
|
| 820 |
+
"model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00003-of-00019.safetensors",
|
| 821 |
+
"model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00003-of-00019.safetensors",
|
| 822 |
+
"model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00003-of-00019.safetensors",
|
| 823 |
+
"model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00003-of-00019.safetensors",
|
| 824 |
+
"model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00003-of-00019.safetensors",
|
| 825 |
+
"model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00003-of-00019.safetensors",
|
| 826 |
+
"model.layers.4.block_sparse_moe.experts.4.w1.weight": "model-00003-of-00019.safetensors",
|
| 827 |
+
"model.layers.4.block_sparse_moe.experts.4.w2.weight": "model-00003-of-00019.safetensors",
|
| 828 |
+
"model.layers.4.block_sparse_moe.experts.4.w3.weight": "model-00003-of-00019.safetensors",
|
| 829 |
+
"model.layers.4.block_sparse_moe.experts.5.w1.weight": "model-00003-of-00019.safetensors",
|
| 830 |
+
"model.layers.4.block_sparse_moe.experts.5.w2.weight": "model-00003-of-00019.safetensors",
|
| 831 |
+
"model.layers.4.block_sparse_moe.experts.5.w3.weight": "model-00003-of-00019.safetensors",
|
| 832 |
+
"model.layers.4.block_sparse_moe.experts.6.w1.weight": "model-00003-of-00019.safetensors",
|
| 833 |
+
"model.layers.4.block_sparse_moe.experts.6.w2.weight": "model-00003-of-00019.safetensors",
|
| 834 |
+
"model.layers.4.block_sparse_moe.experts.6.w3.weight": "model-00003-of-00019.safetensors",
|
| 835 |
+
"model.layers.4.block_sparse_moe.experts.7.w1.weight": "model-00003-of-00019.safetensors",
|
| 836 |
+
"model.layers.4.block_sparse_moe.experts.7.w2.weight": "model-00003-of-00019.safetensors",
|
| 837 |
+
"model.layers.4.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00019.safetensors",
|
| 838 |
+
"model.layers.4.block_sparse_moe.gate.weight": "model-00003-of-00019.safetensors",
|
| 839 |
+
"model.layers.4.input_layernorm.weight": "model-00004-of-00019.safetensors",
|
| 840 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00004-of-00019.safetensors",
|
| 841 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00019.safetensors",
|
| 842 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00019.safetensors",
|
| 843 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00019.safetensors",
|
| 844 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00019.safetensors",
|
| 845 |
+
"model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors",
|
| 846 |
+
"model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors",
|
| 847 |
+
"model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors",
|
| 848 |
+
"model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors",
|
| 849 |
+
"model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors",
|
| 850 |
+
"model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors",
|
| 851 |
+
"model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors",
|
| 852 |
+
"model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors",
|
| 853 |
+
"model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors",
|
| 854 |
+
"model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors",
|
| 855 |
+
"model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors",
|
| 856 |
+
"model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors",
|
| 857 |
+
"model.layers.5.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00019.safetensors",
|
| 858 |
+
"model.layers.5.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00019.safetensors",
|
| 859 |
+
"model.layers.5.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00019.safetensors",
|
| 860 |
+
"model.layers.5.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00019.safetensors",
|
| 861 |
+
"model.layers.5.block_sparse_moe.experts.5.w2.weight": "model-00004-of-00019.safetensors",
|
| 862 |
+
"model.layers.5.block_sparse_moe.experts.5.w3.weight": "model-00004-of-00019.safetensors",
|
| 863 |
+
"model.layers.5.block_sparse_moe.experts.6.w1.weight": "model-00004-of-00019.safetensors",
|
| 864 |
+
"model.layers.5.block_sparse_moe.experts.6.w2.weight": "model-00004-of-00019.safetensors",
|
| 865 |
+
"model.layers.5.block_sparse_moe.experts.6.w3.weight": "model-00004-of-00019.safetensors",
|
| 866 |
+
"model.layers.5.block_sparse_moe.experts.7.w1.weight": "model-00004-of-00019.safetensors",
|
| 867 |
+
"model.layers.5.block_sparse_moe.experts.7.w2.weight": "model-00004-of-00019.safetensors",
|
| 868 |
+
"model.layers.5.block_sparse_moe.experts.7.w3.weight": "model-00004-of-00019.safetensors",
|
| 869 |
+
"model.layers.5.block_sparse_moe.gate.weight": "model-00004-of-00019.safetensors",
|
| 870 |
+
"model.layers.5.input_layernorm.weight": "model-00004-of-00019.safetensors",
|
| 871 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00004-of-00019.safetensors",
|
| 872 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00004-of-00019.safetensors",
|
| 873 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00004-of-00019.safetensors",
|
| 874 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00004-of-00019.safetensors",
|
| 875 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00004-of-00019.safetensors",
|
| 876 |
+
"model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00019.safetensors",
|
| 877 |
+
"model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00019.safetensors",
|
| 878 |
+
"model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00019.safetensors",
|
| 879 |
+
"model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00019.safetensors",
|
| 880 |
+
"model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00019.safetensors",
|
| 881 |
+
"model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00019.safetensors",
|
| 882 |
+
"model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00004-of-00019.safetensors",
|
| 883 |
+
"model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00004-of-00019.safetensors",
|
| 884 |
+
"model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00004-of-00019.safetensors",
|
| 885 |
+
"model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00004-of-00019.safetensors",
|
| 886 |
+
"model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00004-of-00019.safetensors",
|
| 887 |
+
"model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00004-of-00019.safetensors",
|
| 888 |
+
"model.layers.6.block_sparse_moe.experts.4.w1.weight": "model-00004-of-00019.safetensors",
|
| 889 |
+
"model.layers.6.block_sparse_moe.experts.4.w2.weight": "model-00004-of-00019.safetensors",
|
| 890 |
+
"model.layers.6.block_sparse_moe.experts.4.w3.weight": "model-00004-of-00019.safetensors",
|
| 891 |
+
"model.layers.6.block_sparse_moe.experts.5.w1.weight": "model-00004-of-00019.safetensors",
|
| 892 |
+
"model.layers.6.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00019.safetensors",
|
| 893 |
+
"model.layers.6.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors",
|
| 894 |
+
"model.layers.6.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00019.safetensors",
|
| 895 |
+
"model.layers.6.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00019.safetensors",
|
| 896 |
+
"model.layers.6.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00019.safetensors",
|
| 897 |
+
"model.layers.6.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00019.safetensors",
|
| 898 |
+
"model.layers.6.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00019.safetensors",
|
| 899 |
+
"model.layers.6.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00019.safetensors",
|
| 900 |
+
"model.layers.6.block_sparse_moe.gate.weight": "model-00004-of-00019.safetensors",
|
| 901 |
+
"model.layers.6.input_layernorm.weight": "model-00005-of-00019.safetensors",
|
| 902 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00019.safetensors",
|
| 903 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00004-of-00019.safetensors",
|
| 904 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00004-of-00019.safetensors",
|
| 905 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00004-of-00019.safetensors",
|
| 906 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00004-of-00019.safetensors",
|
| 907 |
+
"model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors",
|
| 908 |
+
"model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors",
|
| 909 |
+
"model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors",
|
| 910 |
+
"model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors",
|
| 911 |
+
"model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors",
|
| 912 |
+
"model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors",
|
| 913 |
+
"model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors",
|
| 914 |
+
"model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00019.safetensors",
|
| 915 |
+
"model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors",
|
| 916 |
+
"model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00005-of-00019.safetensors",
|
| 917 |
+
"model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00005-of-00019.safetensors",
|
| 918 |
+
"model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00005-of-00019.safetensors",
|
| 919 |
+
"model.layers.7.block_sparse_moe.experts.4.w1.weight": "model-00005-of-00019.safetensors",
|
| 920 |
+
"model.layers.7.block_sparse_moe.experts.4.w2.weight": "model-00005-of-00019.safetensors",
|
| 921 |
+
"model.layers.7.block_sparse_moe.experts.4.w3.weight": "model-00005-of-00019.safetensors",
|
| 922 |
+
"model.layers.7.block_sparse_moe.experts.5.w1.weight": "model-00005-of-00019.safetensors",
|
| 923 |
+
"model.layers.7.block_sparse_moe.experts.5.w2.weight": "model-00005-of-00019.safetensors",
|
| 924 |
+
"model.layers.7.block_sparse_moe.experts.5.w3.weight": "model-00005-of-00019.safetensors",
|
| 925 |
+
"model.layers.7.block_sparse_moe.experts.6.w1.weight": "model-00005-of-00019.safetensors",
|
| 926 |
+
"model.layers.7.block_sparse_moe.experts.6.w2.weight": "model-00005-of-00019.safetensors",
|
| 927 |
+
"model.layers.7.block_sparse_moe.experts.6.w3.weight": "model-00005-of-00019.safetensors",
|
| 928 |
+
"model.layers.7.block_sparse_moe.experts.7.w1.weight": "model-00005-of-00019.safetensors",
|
| 929 |
+
"model.layers.7.block_sparse_moe.experts.7.w2.weight": "model-00005-of-00019.safetensors",
|
| 930 |
+
"model.layers.7.block_sparse_moe.experts.7.w3.weight": "model-00005-of-00019.safetensors",
|
| 931 |
+
"model.layers.7.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors",
|
| 932 |
+
"model.layers.7.input_layernorm.weight": "model-00005-of-00019.safetensors",
|
| 933 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00019.safetensors",
|
| 934 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00019.safetensors",
|
| 935 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00019.safetensors",
|
| 936 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00019.safetensors",
|
| 937 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00019.safetensors",
|
| 938 |
+
"model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00019.safetensors",
|
| 939 |
+
"model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00019.safetensors",
|
| 940 |
+
"model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00019.safetensors",
|
| 941 |
+
"model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00019.safetensors",
|
| 942 |
+
"model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00019.safetensors",
|
| 943 |
+
"model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00019.safetensors",
|
| 944 |
+
"model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00005-of-00019.safetensors",
|
| 945 |
+
"model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00005-of-00019.safetensors",
|
| 946 |
+
"model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00005-of-00019.safetensors",
|
| 947 |
+
"model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00019.safetensors",
|
| 948 |
+
"model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors",
|
| 949 |
+
"model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors",
|
| 950 |
+
"model.layers.8.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors",
|
| 951 |
+
"model.layers.8.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors",
|
| 952 |
+
"model.layers.8.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors",
|
| 953 |
+
"model.layers.8.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors",
|
| 954 |
+
"model.layers.8.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors",
|
| 955 |
+
"model.layers.8.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors",
|
| 956 |
+
"model.layers.8.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00019.safetensors",
|
| 957 |
+
"model.layers.8.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00019.safetensors",
|
| 958 |
+
"model.layers.8.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00019.safetensors",
|
| 959 |
+
"model.layers.8.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00019.safetensors",
|
| 960 |
+
"model.layers.8.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00019.safetensors",
|
| 961 |
+
"model.layers.8.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00019.safetensors",
|
| 962 |
+
"model.layers.8.block_sparse_moe.gate.weight": "model-00005-of-00019.safetensors",
|
| 963 |
+
"model.layers.8.input_layernorm.weight": "model-00006-of-00019.safetensors",
|
| 964 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00006-of-00019.safetensors",
|
| 965 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00019.safetensors",
|
| 966 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00019.safetensors",
|
| 967 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00019.safetensors",
|
| 968 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00019.safetensors",
|
| 969 |
+
"model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00019.safetensors",
|
| 970 |
+
"model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00019.safetensors",
|
| 971 |
+
"model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00019.safetensors",
|
| 972 |
+
"model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00019.safetensors",
|
| 973 |
+
"model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00019.safetensors",
|
| 974 |
+
"model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00019.safetensors",
|
| 975 |
+
"model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00006-of-00019.safetensors",
|
| 976 |
+
"model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00006-of-00019.safetensors",
|
| 977 |
+
"model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00006-of-00019.safetensors",
|
| 978 |
+
"model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00006-of-00019.safetensors",
|
| 979 |
+
"model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00006-of-00019.safetensors",
|
| 980 |
+
"model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00006-of-00019.safetensors",
|
| 981 |
+
"model.layers.9.block_sparse_moe.experts.4.w1.weight": "model-00006-of-00019.safetensors",
|
| 982 |
+
"model.layers.9.block_sparse_moe.experts.4.w2.weight": "model-00006-of-00019.safetensors",
|
| 983 |
+
"model.layers.9.block_sparse_moe.experts.4.w3.weight": "model-00006-of-00019.safetensors",
|
| 984 |
+
"model.layers.9.block_sparse_moe.experts.5.w1.weight": "model-00006-of-00019.safetensors",
|
| 985 |
+
"model.layers.9.block_sparse_moe.experts.5.w2.weight": "model-00006-of-00019.safetensors",
|
| 986 |
+
"model.layers.9.block_sparse_moe.experts.5.w3.weight": "model-00006-of-00019.safetensors",
|
| 987 |
+
"model.layers.9.block_sparse_moe.experts.6.w1.weight": "model-00006-of-00019.safetensors",
|
| 988 |
+
"model.layers.9.block_sparse_moe.experts.6.w2.weight": "model-00006-of-00019.safetensors",
|
| 989 |
+
"model.layers.9.block_sparse_moe.experts.6.w3.weight": "model-00006-of-00019.safetensors",
|
| 990 |
+
"model.layers.9.block_sparse_moe.experts.7.w1.weight": "model-00006-of-00019.safetensors",
|
| 991 |
+
"model.layers.9.block_sparse_moe.experts.7.w2.weight": "model-00006-of-00019.safetensors",
|
| 992 |
+
"model.layers.9.block_sparse_moe.experts.7.w3.weight": "model-00006-of-00019.safetensors",
|
| 993 |
+
"model.layers.9.block_sparse_moe.gate.weight": "model-00006-of-00019.safetensors",
|
| 994 |
+
"model.layers.9.input_layernorm.weight": "model-00006-of-00019.safetensors",
|
| 995 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00006-of-00019.safetensors",
|
| 996 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00006-of-00019.safetensors",
|
| 997 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00006-of-00019.safetensors",
|
| 998 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00006-of-00019.safetensors",
|
| 999 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00006-of-00019.safetensors",
|
| 1000 |
+
"model.norm.weight": "model-00019-of-00019.safetensors"
|
| 1001 |
+
}
|
| 1002 |
+
}
|
output-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bafd06bf09d4b17b4e0b2f86031adc81ab108341bf1526819e57357d218892c3
|
| 3 |
+
size 8586584368
|
output-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:217b29a3c65a3fea0b5a649a8d6dff691fc57e03c1760b05f46ffa9a95c4b0b4
|
| 3 |
+
size 8590025856
|
output-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04e6c6806a8372d9d50bc0976fc5d92e0c48ee95b54445fc60b43345696520ab
|
| 3 |
+
size 8563276616
|
output-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37d848eb94a8b69356149b758b0b135caf4e0b91d773cc0ad0d351c86c7c594c
|
| 3 |
+
size 3956936176
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
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 sha256:86840d604f9e18ebbdc35aa937cfc2486fe774534ceea0fd3f667a72bc7584b2
|
| 3 |
+
size 925420
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
}
|
| 29 |
+
},
|
| 30 |
+
"additional_special_tokens": [],
|
| 31 |
+
"bos_token": "<s>",
|
| 32 |
+
"clean_up_tokenization_spaces": false,
|
| 33 |
+
"eos_token": "</s>",
|
| 34 |
+
"legacy": true,
|
| 35 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": null,
|
| 37 |
+
"sp_model_kwargs": {},
|
| 38 |
+
"spaces_between_special_tokens": false,
|
| 39 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 40 |
+
"unk_token": "<unk>",
|
| 41 |
+
"use_default_system_prompt": false
|
| 42 |
+
}
|