Upload folder using huggingface_hub
Browse files- README.md +300 -0
- added_tokens.json +24 -0
- config.json +28 -0
- mergekit_config.yml +157 -0
- merges.txt +0 -0
- model-00001-of-00006.safetensors +3 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +31 -0
- tokenizer.json +0 -0
- tokenizer_config.json +207 -0
- vocab.json +0 -0
README.md
ADDED
|
@@ -0,0 +1,300 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- win10/Qwen2.5-2B-Instruct
|
| 4 |
+
- win10/Qwen2.5-2B-Instruct
|
| 5 |
+
- win10/Qwen2.5-2B-Instruct
|
| 6 |
+
- win10/Qwen2.5-2B-Instruct
|
| 7 |
+
- win10/Qwen2.5-2B-Instruct
|
| 8 |
+
- win10/Qwen2.5-2B-Instruct
|
| 9 |
+
- win10/Qwen2.5-2B-Instruct
|
| 10 |
+
- win10/Qwen2.5-2B-Instruct
|
| 11 |
+
- win10/Qwen2.5-2B-Instruct
|
| 12 |
+
- win10/Qwen2.5-2B-Instruct
|
| 13 |
+
- win10/Qwen2.5-2B-Instruct
|
| 14 |
+
- win10/Qwen2.5-2B-Instruct
|
| 15 |
+
- win10/Qwen2.5-2B-Instruct
|
| 16 |
+
- win10/Qwen2.5-2B-Instruct
|
| 17 |
+
- win10/Qwen2.5-2B-Instruct
|
| 18 |
+
- win10/Qwen2.5-2B-Instruct
|
| 19 |
+
- win10/Qwen2.5-2B-Instruct
|
| 20 |
+
- win10/Qwen2.5-2B-Instruct
|
| 21 |
+
- win10/Qwen2.5-2B-Instruct
|
| 22 |
+
- win10/Qwen2.5-2B-Instruct
|
| 23 |
+
- win10/Qwen2.5-2B-Instruct
|
| 24 |
+
- win10/Qwen2.5-2B-Instruct
|
| 25 |
+
- win10/Qwen2.5-2B-Instruct
|
| 26 |
+
- win10/Qwen2.5-2B-Instruct
|
| 27 |
+
- win10/Qwen2.5-2B-Instruct
|
| 28 |
+
- win10/Qwen2.5-2B-Instruct
|
| 29 |
+
- win10/Qwen2.5-2B-Instruct
|
| 30 |
+
- win10/Qwen2.5-2B-Instruct
|
| 31 |
+
- win10/Qwen2.5-2B-Instruct
|
| 32 |
+
- win10/Qwen2.5-2B-Instruct
|
| 33 |
+
- win10/Qwen2.5-2B-Instruct
|
| 34 |
+
- win10/Qwen2.5-2B-Instruct
|
| 35 |
+
- win10/Qwen2.5-2B-Instruct
|
| 36 |
+
- win10/Qwen2.5-2B-Instruct
|
| 37 |
+
- win10/Qwen2.5-2B-Instruct
|
| 38 |
+
- win10/Qwen2.5-2B-Instruct
|
| 39 |
+
- win10/Qwen2.5-2B-Instruct
|
| 40 |
+
- win10/Qwen2.5-2B-Instruct
|
| 41 |
+
- win10/Qwen2.5-2B-Instruct
|
| 42 |
+
- win10/Qwen2.5-2B-Instruct
|
| 43 |
+
- win10/Qwen2.5-2B-Instruct
|
| 44 |
+
- win10/Qwen2.5-2B-Instruct
|
| 45 |
+
- win10/Qwen2.5-2B-Instruct
|
| 46 |
+
- win10/Qwen2.5-2B-Instruct
|
| 47 |
+
- win10/Qwen2.5-2B-Instruct
|
| 48 |
+
- win10/Qwen2.5-2B-Instruct
|
| 49 |
+
- win10/Qwen2.5-2B-Instruct
|
| 50 |
+
- win10/Qwen2.5-2B-Instruct
|
| 51 |
+
- win10/Qwen2.5-2B-Instruct
|
| 52 |
+
- win10/Qwen2.5-2B-Instruct
|
| 53 |
+
- win10/Qwen2.5-2B-Instruct
|
| 54 |
+
tags:
|
| 55 |
+
- merge
|
| 56 |
+
- mergekit
|
| 57 |
+
- lazymergekit
|
| 58 |
+
- win10/Qwen2.5-2B-Instruct
|
| 59 |
+
---
|
| 60 |
+
|
| 61 |
+
# Qwen2.5-4B-Instruct
|
| 62 |
+
|
| 63 |
+
Qwen2.5-4B-Instruct is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
| 64 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 65 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 66 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 67 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 68 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 69 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 70 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 71 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 72 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 73 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 74 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 75 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 76 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 77 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 78 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 79 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 80 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 81 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 82 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 83 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 84 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 85 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 86 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 87 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 88 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 89 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 90 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 91 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 92 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 93 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 94 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 95 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 96 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 97 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 98 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 99 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 100 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 101 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 102 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 103 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 104 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 105 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 106 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 107 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 108 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 109 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 110 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 111 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 112 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 113 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 114 |
+
* [win10/Qwen2.5-2B-Instruct](https://huggingface.co/win10/Qwen2.5-2B-Instruct)
|
| 115 |
+
|
| 116 |
+
## 🧩 Configuration
|
| 117 |
+
|
| 118 |
+
```yaml
|
| 119 |
+
dtype: bfloat16
|
| 120 |
+
merge_method: passthrough
|
| 121 |
+
slices:
|
| 122 |
+
- sources:
|
| 123 |
+
- layer_range: [0, 2]
|
| 124 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 125 |
+
- sources:
|
| 126 |
+
- layer_range: [1, 3]
|
| 127 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 128 |
+
- sources:
|
| 129 |
+
- layer_range: [2, 4]
|
| 130 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 131 |
+
- sources:
|
| 132 |
+
- layer_range: [3, 5]
|
| 133 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 134 |
+
- sources:
|
| 135 |
+
- layer_range: [4, 6]
|
| 136 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 137 |
+
- sources:
|
| 138 |
+
- layer_range: [5, 7]
|
| 139 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 140 |
+
- sources:
|
| 141 |
+
- layer_range: [6, 8]
|
| 142 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 143 |
+
- sources:
|
| 144 |
+
- layer_range: [7, 9]
|
| 145 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 146 |
+
- sources:
|
| 147 |
+
- layer_range: [8, 10]
|
| 148 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 149 |
+
- sources:
|
| 150 |
+
- layer_range: [9, 11]
|
| 151 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 152 |
+
- sources:
|
| 153 |
+
- layer_range: [10, 12]
|
| 154 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 155 |
+
- sources:
|
| 156 |
+
- layer_range: [11, 13]
|
| 157 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 158 |
+
- sources:
|
| 159 |
+
- layer_range: [12, 14]
|
| 160 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 161 |
+
- sources:
|
| 162 |
+
- layer_range: [13, 15]
|
| 163 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 164 |
+
- sources:
|
| 165 |
+
- layer_range: [14, 16]
|
| 166 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 167 |
+
- sources:
|
| 168 |
+
- layer_range: [15, 17]
|
| 169 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 170 |
+
- sources:
|
| 171 |
+
- layer_range: [16, 18]
|
| 172 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 173 |
+
- sources:
|
| 174 |
+
- layer_range: [17, 19]
|
| 175 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 176 |
+
- sources:
|
| 177 |
+
- layer_range: [18, 20]
|
| 178 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 179 |
+
- sources:
|
| 180 |
+
- layer_range: [19, 21]
|
| 181 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 182 |
+
- sources:
|
| 183 |
+
- layer_range: [20, 22]
|
| 184 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 185 |
+
- sources:
|
| 186 |
+
- layer_range: [21, 23]
|
| 187 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 188 |
+
- sources:
|
| 189 |
+
- layer_range: [22, 24]
|
| 190 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 191 |
+
- sources:
|
| 192 |
+
- layer_range: [23, 25]
|
| 193 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 194 |
+
- sources:
|
| 195 |
+
- layer_range: [24, 26]
|
| 196 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 197 |
+
- sources:
|
| 198 |
+
- layer_range: [25, 27]
|
| 199 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 200 |
+
- sources:
|
| 201 |
+
- layer_range: [26, 28]
|
| 202 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 203 |
+
- sources:
|
| 204 |
+
- layer_range: [27, 29]
|
| 205 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 206 |
+
- sources:
|
| 207 |
+
- layer_range: [28, 30]
|
| 208 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 209 |
+
- sources:
|
| 210 |
+
- layer_range: [29, 31]
|
| 211 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 212 |
+
- sources:
|
| 213 |
+
- layer_range: [30, 32]
|
| 214 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 215 |
+
- sources:
|
| 216 |
+
- layer_range: [31, 33]
|
| 217 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 218 |
+
- sources:
|
| 219 |
+
- layer_range: [32, 34]
|
| 220 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 221 |
+
- sources:
|
| 222 |
+
- layer_range: [33, 35]
|
| 223 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 224 |
+
- sources:
|
| 225 |
+
- layer_range: [34, 36]
|
| 226 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 227 |
+
- sources:
|
| 228 |
+
- layer_range: [35, 37]
|
| 229 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 230 |
+
- sources:
|
| 231 |
+
- layer_range: [36, 38]
|
| 232 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 233 |
+
- sources:
|
| 234 |
+
- layer_range: [37, 39]
|
| 235 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 236 |
+
- sources:
|
| 237 |
+
- layer_range: [38, 40]
|
| 238 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 239 |
+
- sources:
|
| 240 |
+
- layer_range: [39, 41]
|
| 241 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 242 |
+
- sources:
|
| 243 |
+
- layer_range: [40, 42]
|
| 244 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 245 |
+
- sources:
|
| 246 |
+
- layer_range: [41, 43]
|
| 247 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 248 |
+
- sources:
|
| 249 |
+
- layer_range: [42, 44]
|
| 250 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 251 |
+
- sources:
|
| 252 |
+
- layer_range: [43, 45]
|
| 253 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 254 |
+
- sources:
|
| 255 |
+
- layer_range: [44, 46]
|
| 256 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 257 |
+
- sources:
|
| 258 |
+
- layer_range: [45, 47]
|
| 259 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 260 |
+
- sources:
|
| 261 |
+
- layer_range: [46, 48]
|
| 262 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 263 |
+
- sources:
|
| 264 |
+
- layer_range: [47, 49]
|
| 265 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 266 |
+
- sources:
|
| 267 |
+
- layer_range: [48, 50]
|
| 268 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 269 |
+
- sources:
|
| 270 |
+
- layer_range: [49, 51]
|
| 271 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 272 |
+
- sources:
|
| 273 |
+
- layer_range: [50, 52]
|
| 274 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 275 |
+
```
|
| 276 |
+
|
| 277 |
+
## 💻 Usage
|
| 278 |
+
|
| 279 |
+
```python
|
| 280 |
+
!pip install -qU transformers accelerate
|
| 281 |
+
|
| 282 |
+
from transformers import AutoTokenizer
|
| 283 |
+
import transformers
|
| 284 |
+
import torch
|
| 285 |
+
|
| 286 |
+
model = "win10/Qwen2.5-4B-Instruct"
|
| 287 |
+
messages = [{"role": "user", "content": "What is a large language model?"}]
|
| 288 |
+
|
| 289 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
| 290 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
| 291 |
+
pipeline = transformers.pipeline(
|
| 292 |
+
"text-generation",
|
| 293 |
+
model=model,
|
| 294 |
+
torch_dtype=torch.float16,
|
| 295 |
+
device_map="auto",
|
| 296 |
+
)
|
| 297 |
+
|
| 298 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
| 299 |
+
print(outputs[0]["generated_text"])
|
| 300 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "win10/Qwen2.5-2B-Instruct",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1536,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 8960,
|
| 13 |
+
"max_position_embeddings": 32768,
|
| 14 |
+
"max_window_layers": 21,
|
| 15 |
+
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 12,
|
| 17 |
+
"num_hidden_layers": 102,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_theta": 1000000.0,
|
| 21 |
+
"sliding_window": null,
|
| 22 |
+
"tie_word_embeddings": true,
|
| 23 |
+
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.44.2",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"use_sliding_window": false,
|
| 27 |
+
"vocab_size": 151936
|
| 28 |
+
}
|
mergekit_config.yml
ADDED
|
@@ -0,0 +1,157 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
dtype: bfloat16
|
| 3 |
+
merge_method: passthrough
|
| 4 |
+
slices:
|
| 5 |
+
- sources:
|
| 6 |
+
- layer_range: [0, 2]
|
| 7 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 8 |
+
- sources:
|
| 9 |
+
- layer_range: [1, 3]
|
| 10 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 11 |
+
- sources:
|
| 12 |
+
- layer_range: [2, 4]
|
| 13 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 14 |
+
- sources:
|
| 15 |
+
- layer_range: [3, 5]
|
| 16 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 17 |
+
- sources:
|
| 18 |
+
- layer_range: [4, 6]
|
| 19 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 20 |
+
- sources:
|
| 21 |
+
- layer_range: [5, 7]
|
| 22 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 23 |
+
- sources:
|
| 24 |
+
- layer_range: [6, 8]
|
| 25 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 26 |
+
- sources:
|
| 27 |
+
- layer_range: [7, 9]
|
| 28 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 29 |
+
- sources:
|
| 30 |
+
- layer_range: [8, 10]
|
| 31 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 32 |
+
- sources:
|
| 33 |
+
- layer_range: [9, 11]
|
| 34 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 35 |
+
- sources:
|
| 36 |
+
- layer_range: [10, 12]
|
| 37 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 38 |
+
- sources:
|
| 39 |
+
- layer_range: [11, 13]
|
| 40 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 41 |
+
- sources:
|
| 42 |
+
- layer_range: [12, 14]
|
| 43 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 44 |
+
- sources:
|
| 45 |
+
- layer_range: [13, 15]
|
| 46 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 47 |
+
- sources:
|
| 48 |
+
- layer_range: [14, 16]
|
| 49 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 50 |
+
- sources:
|
| 51 |
+
- layer_range: [15, 17]
|
| 52 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 53 |
+
- sources:
|
| 54 |
+
- layer_range: [16, 18]
|
| 55 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 56 |
+
- sources:
|
| 57 |
+
- layer_range: [17, 19]
|
| 58 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 59 |
+
- sources:
|
| 60 |
+
- layer_range: [18, 20]
|
| 61 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 62 |
+
- sources:
|
| 63 |
+
- layer_range: [19, 21]
|
| 64 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 65 |
+
- sources:
|
| 66 |
+
- layer_range: [20, 22]
|
| 67 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 68 |
+
- sources:
|
| 69 |
+
- layer_range: [21, 23]
|
| 70 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 71 |
+
- sources:
|
| 72 |
+
- layer_range: [22, 24]
|
| 73 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 74 |
+
- sources:
|
| 75 |
+
- layer_range: [23, 25]
|
| 76 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 77 |
+
- sources:
|
| 78 |
+
- layer_range: [24, 26]
|
| 79 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 80 |
+
- sources:
|
| 81 |
+
- layer_range: [25, 27]
|
| 82 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 83 |
+
- sources:
|
| 84 |
+
- layer_range: [26, 28]
|
| 85 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 86 |
+
- sources:
|
| 87 |
+
- layer_range: [27, 29]
|
| 88 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 89 |
+
- sources:
|
| 90 |
+
- layer_range: [28, 30]
|
| 91 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 92 |
+
- sources:
|
| 93 |
+
- layer_range: [29, 31]
|
| 94 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 95 |
+
- sources:
|
| 96 |
+
- layer_range: [30, 32]
|
| 97 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 98 |
+
- sources:
|
| 99 |
+
- layer_range: [31, 33]
|
| 100 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 101 |
+
- sources:
|
| 102 |
+
- layer_range: [32, 34]
|
| 103 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 104 |
+
- sources:
|
| 105 |
+
- layer_range: [33, 35]
|
| 106 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 107 |
+
- sources:
|
| 108 |
+
- layer_range: [34, 36]
|
| 109 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 110 |
+
- sources:
|
| 111 |
+
- layer_range: [35, 37]
|
| 112 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 113 |
+
- sources:
|
| 114 |
+
- layer_range: [36, 38]
|
| 115 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 116 |
+
- sources:
|
| 117 |
+
- layer_range: [37, 39]
|
| 118 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 119 |
+
- sources:
|
| 120 |
+
- layer_range: [38, 40]
|
| 121 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 122 |
+
- sources:
|
| 123 |
+
- layer_range: [39, 41]
|
| 124 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 125 |
+
- sources:
|
| 126 |
+
- layer_range: [40, 42]
|
| 127 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 128 |
+
- sources:
|
| 129 |
+
- layer_range: [41, 43]
|
| 130 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 131 |
+
- sources:
|
| 132 |
+
- layer_range: [42, 44]
|
| 133 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 134 |
+
- sources:
|
| 135 |
+
- layer_range: [43, 45]
|
| 136 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 137 |
+
- sources:
|
| 138 |
+
- layer_range: [44, 46]
|
| 139 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 140 |
+
- sources:
|
| 141 |
+
- layer_range: [45, 47]
|
| 142 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 143 |
+
- sources:
|
| 144 |
+
- layer_range: [46, 48]
|
| 145 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 146 |
+
- sources:
|
| 147 |
+
- layer_range: [47, 49]
|
| 148 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 149 |
+
- sources:
|
| 150 |
+
- layer_range: [48, 50]
|
| 151 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 152 |
+
- sources:
|
| 153 |
+
- layer_range: [49, 51]
|
| 154 |
+
model: win10/Qwen2.5-2B-Instruct
|
| 155 |
+
- sources:
|
| 156 |
+
- layer_range: [50, 52]
|
| 157 |
+
model: win10/Qwen2.5-2B-Instruct
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c8c478d564badb11e287b2be425f430e0811c0eb91168c5280a828d4dd1740c
|
| 3 |
+
size 988548664
|
model-00001-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c8c478d564badb11e287b2be425f430e0811c0eb91168c5280a828d4dd1740c
|
| 3 |
+
size 988548664
|
model-00002-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03acc7b5a9b3f44c87001ca013f783a1068654e331dfcfb9a6f128efa6b85883
|
| 3 |
+
size 974519704
|
model-00002-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd305a43e7026cac9078fab0c1bef3e5d4f47c15373a9b325b45e19f81ec9cf6
|
| 3 |
+
size 974519704
|
model-00003-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93522ba549a8971e8cd1952bc31f440c2697f8369062c9edfa6f42566b2d9da6
|
| 3 |
+
size 991020488
|
model-00003-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ccc27fe2650f0885d754f21e2fae08c0a9afc9dc481aab9ee3cec08cf66628a
|
| 3 |
+
size 991020488
|
model-00004-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25d5635465bf9b07c99abce5429c794ca4c43b53d6496abd5e08d5ffb4464589
|
| 3 |
+
size 991020464
|
model-00004-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:555e777bc6140c53081dce01f58854a20f2567a0774e90f915359f8ff556087e
|
| 3 |
+
size 991020456
|
model-00005-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6d0181b6b7a4150af03e7e4a4cafea53407a7d710b794d4abb4d689d7b46a33
|
| 3 |
+
size 974516488
|
model-00005-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e27b8bbb42694b8b9ace7a1fb4e83fe714b61923220725e905c8ed32ebf89ca0
|
| 3 |
+
size 997319896
|
model-00006-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9667c0cada7c3f1e0d540c015a08bd3597b45a8cb950c86da4b274034e9fb186
|
| 3 |
+
size 880916344
|
model-00006-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:819a5240f2a8a3836ead62f4eb6696eb9034baf9169d727eae172e3c89f4a33e
|
| 3 |
+
size 979238400
|
model-00007-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b47fb11ada77b468e7a0b85599c8ff0d5bd4b27458368166bee64c6efd41b701
|
| 3 |
+
size 991020488
|
model-00008-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:906f5d8f57f4e2cb273ddcff91ab1ae0232f472d4c2fd8cb797ae68fb2dd6db8
|
| 3 |
+
size 991020456
|
model-00009-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:436ea9b68afd00ceccb15e789e6baba59787483f1451f631480a72dfb7de99d7
|
| 3 |
+
size 985537848
|
model-00010-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b76cb0e89b3f69472ce497928a72c6cb98076e22df9f55929501710e6c9acd8
|
| 3 |
+
size 979999184
|
model-00011-of-00011.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f42c081cd2855d9b3635ef707d3839f1e1ecad363ed9c10326c080654e1ce3a
|
| 3 |
+
size 611146640
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 10480253952}, "weight_map": {"lm_head.weight": "model-00001-of-00011.safetensors", "model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00011.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00011.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00011.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00011.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00011.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00011.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00011.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00011.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00011.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00011.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00011.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00011.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00011.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00011.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00011.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00003-of-00011.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00003-of-00011.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00003-of-00011.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00004-of-00011.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00004-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00004-of-00011.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00004-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00004-of-00011.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00004-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00004-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00004-of-00011.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00004-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00004-of-00011.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00004-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00004-of-00011.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00004-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00004-of-00011.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00004-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00004-of-00011.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00004-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00004-of-00011.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00004-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00004-of-00011.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00004-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00004-of-00011.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00004-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00004-of-00011.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00004-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00005-of-00011.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00005-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00005-of-00011.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00005-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00005-of-00011.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00005-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.48.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00005-of-00011.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00005-of-00011.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00005-of-00011.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00005-of-00011.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00005-of-00011.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00005-of-00011.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.50.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.49.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00005-of-00011.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00005-of-00011.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00005-of-00011.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00005-of-00011.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00005-of-00011.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00005-of-00011.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.52.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.51.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00005-of-00011.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00005-of-00011.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00005-of-00011.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00005-of-00011.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00005-of-00011.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00005-of-00011.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.54.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.53.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00005-of-00011.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00005-of-00011.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00005-of-00011.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00005-of-00011.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00005-of-00011.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00005-of-00011.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.56.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.55.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00005-of-00011.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00005-of-00011.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00006-of-00011.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00006-of-00011.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00006-of-00011.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00006-of-00011.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.58.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.57.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00006-of-00011.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00006-of-00011.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00006-of-00011.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00006-of-00011.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00006-of-00011.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00006-of-00011.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00006-of-00011.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00006-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00006-of-00011.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00006-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00006-of-00011.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00006-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.60.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.59.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00006-of-00011.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00006-of-00011.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00006-of-00011.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00006-of-00011.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00006-of-00011.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00006-of-00011.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.62.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.61.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00006-of-00011.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00006-of-00011.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00006-of-00011.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00006-of-00011.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00006-of-00011.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00006-of-00011.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.64.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.63.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00006-of-00011.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00006-of-00011.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00006-of-00011.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00006-of-00011.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00006-of-00011.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00006-of-00011.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.66.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.65.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00007-of-00011.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00007-of-00011.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00007-of-00011.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00007-of-00011.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00007-of-00011.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00007-of-00011.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.68.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.67.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00007-of-00011.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00007-of-00011.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00007-of-00011.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00007-of-00011.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00007-of-00011.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00007-of-00011.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.70.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.69.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00007-of-00011.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00007-of-00011.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00007-of-00011.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00007-of-00011.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00007-of-00011.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00007-of-00011.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.72.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.71.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00007-of-00011.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00007-of-00011.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00007-of-00011.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00007-of-00011.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00007-of-00011.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00007-of-00011.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.74.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.73.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00007-of-00011.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00007-of-00011.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00007-of-00011.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00007-of-00011.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00007-of-00011.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00007-of-00011.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.76.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.75.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00008-of-00011.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00008-of-00011.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00008-of-00011.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00008-of-00011.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00008-of-00011.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00008-of-00011.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.78.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.77.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00008-of-00011.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00008-of-00011.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00008-of-00011.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00008-of-00011.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00008-of-00011.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00008-of-00011.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00008-of-00011.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00008-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00008-of-00011.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00008-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00008-of-00011.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00008-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.80.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.79.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.80.self_attn.k_proj.bias": "model-00008-of-00011.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00008-of-00011.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.80.self_attn.q_proj.bias": "model-00008-of-00011.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00008-of-00011.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.80.self_attn.v_proj.bias": "model-00008-of-00011.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00008-of-00011.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.82.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.81.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.82.self_attn.k_proj.bias": "model-00008-of-00011.safetensors", "model.layers.81.self_attn.k_proj.bias": "model-00008-of-00011.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.82.self_attn.q_proj.bias": "model-00008-of-00011.safetensors", "model.layers.81.self_attn.q_proj.bias": "model-00008-of-00011.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.82.self_attn.v_proj.bias": "model-00008-of-00011.safetensors", "model.layers.81.self_attn.v_proj.bias": "model-00008-of-00011.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.84.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.83.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.84.self_attn.k_proj.bias": "model-00009-of-00011.safetensors", "model.layers.83.self_attn.k_proj.bias": "model-00009-of-00011.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.84.self_attn.q_proj.bias": "model-00009-of-00011.safetensors", "model.layers.83.self_attn.q_proj.bias": "model-00009-of-00011.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.84.self_attn.v_proj.bias": "model-00009-of-00011.safetensors", "model.layers.83.self_attn.v_proj.bias": "model-00009-of-00011.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.86.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.85.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.86.self_attn.k_proj.bias": "model-00009-of-00011.safetensors", "model.layers.85.self_attn.k_proj.bias": "model-00009-of-00011.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.86.self_attn.q_proj.bias": "model-00009-of-00011.safetensors", "model.layers.85.self_attn.q_proj.bias": "model-00009-of-00011.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.86.self_attn.v_proj.bias": "model-00009-of-00011.safetensors", "model.layers.85.self_attn.v_proj.bias": "model-00009-of-00011.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.88.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.87.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.88.self_attn.k_proj.bias": "model-00009-of-00011.safetensors", "model.layers.87.self_attn.k_proj.bias": "model-00009-of-00011.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.88.self_attn.q_proj.bias": "model-00009-of-00011.safetensors", "model.layers.87.self_attn.q_proj.bias": "model-00009-of-00011.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.88.self_attn.v_proj.bias": "model-00009-of-00011.safetensors", "model.layers.87.self_attn.v_proj.bias": "model-00009-of-00011.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.90.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.89.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.90.self_attn.k_proj.bias": "model-00009-of-00011.safetensors", "model.layers.89.self_attn.k_proj.bias": "model-00009-of-00011.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.90.self_attn.q_proj.bias": "model-00009-of-00011.safetensors", "model.layers.89.self_attn.q_proj.bias": "model-00009-of-00011.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.90.self_attn.v_proj.bias": "model-00009-of-00011.safetensors", "model.layers.89.self_attn.v_proj.bias": "model-00009-of-00011.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.92.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.91.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.92.self_attn.k_proj.bias": "model-00009-of-00011.safetensors", "model.layers.91.self_attn.k_proj.bias": "model-00009-of-00011.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.92.self_attn.q_proj.bias": "model-00009-of-00011.safetensors", "model.layers.91.self_attn.q_proj.bias": "model-00009-of-00011.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.92.self_attn.v_proj.bias": "model-00009-of-00011.safetensors", "model.layers.91.self_attn.v_proj.bias": "model-00009-of-00011.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.94.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.93.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.94.self_attn.k_proj.bias": "model-00009-of-00011.safetensors", "model.layers.93.self_attn.k_proj.bias": "model-00009-of-00011.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.94.self_attn.q_proj.bias": "model-00009-of-00011.safetensors", "model.layers.93.self_attn.q_proj.bias": "model-00009-of-00011.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.94.self_attn.v_proj.bias": "model-00009-of-00011.safetensors", "model.layers.93.self_attn.v_proj.bias": "model-00009-of-00011.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.96.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.95.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.96.self_attn.k_proj.bias": "model-00010-of-00011.safetensors", "model.layers.95.self_attn.k_proj.bias": "model-00010-of-00011.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.96.self_attn.q_proj.bias": "model-00010-of-00011.safetensors", "model.layers.95.self_attn.q_proj.bias": "model-00010-of-00011.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.96.self_attn.v_proj.bias": "model-00010-of-00011.safetensors", "model.layers.95.self_attn.v_proj.bias": "model-00010-of-00011.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.98.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.97.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.98.self_attn.k_proj.bias": "model-00010-of-00011.safetensors", "model.layers.97.self_attn.k_proj.bias": "model-00010-of-00011.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.98.self_attn.q_proj.bias": "model-00010-of-00011.safetensors", "model.layers.97.self_attn.q_proj.bias": "model-00010-of-00011.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.98.self_attn.v_proj.bias": "model-00010-of-00011.safetensors", "model.layers.97.self_attn.v_proj.bias": "model-00010-of-00011.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00010-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.100.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.99.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.100.self_attn.k_proj.bias": "model-00010-of-00011.safetensors", "model.layers.99.self_attn.k_proj.bias": "model-00010-of-00011.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.100.self_attn.q_proj.bias": "model-00010-of-00011.safetensors", "model.layers.99.self_attn.q_proj.bias": "model-00010-of-00011.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.100.self_attn.v_proj.bias": "model-00010-of-00011.safetensors", "model.layers.99.self_attn.v_proj.bias": "model-00010-of-00011.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.101.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.101.self_attn.k_proj.bias": "model-00010-of-00011.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.101.self_attn.q_proj.bias": "model-00010-of-00011.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.101.self_attn.v_proj.bias": "model-00010-of-00011.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00011-of-00011.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00011-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00011-of-00011.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00011-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00011-of-00011.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00011-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00011-of-00011.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00011-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00011-of-00011.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00011-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00011-of-00011.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00011-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00011-of-00011.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00011-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00011-of-00011.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00011-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00011-of-00011.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00011-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00011-of-00011.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00011-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00011-of-00011.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00011-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00011-of-00011.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00011-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,207 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"model_max_length": 131072,
|
| 203 |
+
"pad_token": "<|endoftext|>",
|
| 204 |
+
"split_special_tokens": false,
|
| 205 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 206 |
+
"unk_token": null
|
| 207 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|