Upload folder using huggingface_hub
#1
by
shawhin
- opened
- README.md +8 -11
- config.json +4 -7
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors +2 -2
- model.safetensors.index.json +292 -742
- tokenizer.json +7 -16
- tokenizer_config.json +3 -2
README.md
CHANGED
|
@@ -1,28 +1,25 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
| 3 |
tags:
|
| 4 |
- finetuned
|
| 5 |
- mlx
|
| 6 |
-
pipeline_tag: text-generation
|
| 7 |
inference: true
|
| 8 |
widget:
|
| 9 |
- messages:
|
| 10 |
- role: user
|
| 11 |
content: What is your favorite condiment?
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
|
| 14 |
-
#
|
| 15 |
This model was converted to MLX format from [`mistralai/Mistral-7B-Instruct-v0.2`]().
|
| 16 |
Refer to the [original model card](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) for more details on the model.
|
| 17 |
## Use with mlx
|
| 18 |
-
|
| 19 |
```bash
|
| 20 |
-
pip install mlx
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
from mlx_lm import load, generate
|
| 25 |
-
|
| 26 |
-
model, tokenizer = load("mlx-community/Mistral-7B-Instruct-v0.2-4bit")
|
| 27 |
-
response = generate(model, tokenizer, prompt="hello", verbose=True)
|
| 28 |
```
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
pipeline_tag: text-generation
|
| 4 |
tags:
|
| 5 |
- finetuned
|
| 6 |
- mlx
|
|
|
|
| 7 |
inference: true
|
| 8 |
widget:
|
| 9 |
- messages:
|
| 10 |
- role: user
|
| 11 |
content: What is your favorite condiment?
|
| 12 |
+
extra_gated_description: If you want to learn more about how we process your personal
|
| 13 |
+
data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
|
| 14 |
---
|
| 15 |
|
| 16 |
+
# Mistral-7B-Instruct-v0.2-4bit
|
| 17 |
This model was converted to MLX format from [`mistralai/Mistral-7B-Instruct-v0.2`]().
|
| 18 |
Refer to the [original model card](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) for more details on the model.
|
| 19 |
## Use with mlx
|
|
|
|
| 20 |
```bash
|
| 21 |
+
pip install mlx
|
| 22 |
+
git clone https://github.com/ml-explore/mlx-examples.git
|
| 23 |
+
cd mlx-examples/llms/hf_llm
|
| 24 |
+
python generate.py --model mlx-community/Mistral-7B-Instruct-v0.2-4bit --prompt "My name is"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
```
|
config.json
CHANGED
|
@@ -6,6 +6,7 @@
|
|
| 6 |
"num_hidden_layers": 32,
|
| 7 |
"num_attention_heads": 32,
|
| 8 |
"sliding_window": null,
|
|
|
|
| 9 |
"num_key_value_heads": 8,
|
| 10 |
"hidden_act": "silu",
|
| 11 |
"initializer_range": 0.02,
|
|
@@ -74,11 +75,7 @@
|
|
| 74 |
"decoder_start_token_id": null,
|
| 75 |
"task_specific_params": null,
|
| 76 |
"problem_type": null,
|
| 77 |
-
"_name_or_path": "/
|
| 78 |
-
"transformers_version": "4.
|
| 79 |
-
"model_type": "mistral"
|
| 80 |
-
"quantization": {
|
| 81 |
-
"group_size": 64,
|
| 82 |
-
"bits": 4
|
| 83 |
-
}
|
| 84 |
}
|
|
|
|
| 6 |
"num_hidden_layers": 32,
|
| 7 |
"num_attention_heads": 32,
|
| 8 |
"sliding_window": null,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
"num_key_value_heads": 8,
|
| 11 |
"hidden_act": "silu",
|
| 12 |
"initializer_range": 0.02,
|
|
|
|
| 75 |
"decoder_start_token_id": null,
|
| 76 |
"task_specific_params": null,
|
| 77 |
"problem_type": null,
|
| 78 |
+
"_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
| 79 |
+
"transformers_version": "4.43.1",
|
| 80 |
+
"model_type": "mistral"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
}
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87944fa60467ff4db519e6446339e664aa890fb00da967d8f78c4cdcbfed190b
|
| 3 |
+
size 5352158207
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d8426a4db47a8646c94a398d09ac5751f1aac106e0f1bff22f8e92c7ae46b4c
|
| 3 |
+
size 5303897790
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:028b45260467233d67377af4c69a1f0dc7eaf061c7af321fbbec04ed3c824146
|
| 3 |
+
size 3827441722
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3d8c9628cd71db60c7e42c33fd2e0e47ea02b98b57597dd6a9613394d6d92ca
|
| 3 |
+
size 4073941269
|
model.safetensors.index.json
CHANGED
|
@@ -1,748 +1,298 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"lm_head.
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"model.
|
| 10 |
-
"model.layers.0.
|
| 11 |
-
"model.layers.0.mlp.
|
| 12 |
-
"model.layers.0.
|
| 13 |
-
"model.layers.0.
|
| 14 |
-
"model.layers.0.
|
| 15 |
-
"model.layers.0.
|
| 16 |
-
"model.layers.0.
|
| 17 |
-
"model.layers.
|
| 18 |
-
"model.layers.
|
| 19 |
-
"model.layers.
|
| 20 |
-
"model.layers.
|
| 21 |
-
"model.layers.
|
| 22 |
-
"model.layers.
|
| 23 |
-
"model.layers.
|
| 24 |
-
"model.layers.
|
| 25 |
-
"model.layers.
|
| 26 |
-
"model.layers.
|
| 27 |
-
"model.layers.
|
| 28 |
-
"model.layers.
|
| 29 |
-
"model.layers.
|
| 30 |
-
"model.layers.
|
| 31 |
-
"model.layers.
|
| 32 |
-
"model.layers.
|
| 33 |
-
"model.layers.
|
| 34 |
-
"model.layers.
|
| 35 |
-
"model.layers.
|
| 36 |
-
"model.layers.
|
| 37 |
-
"model.layers.
|
| 38 |
-
"model.layers.
|
| 39 |
-
"model.layers.
|
| 40 |
-
"model.layers.
|
| 41 |
-
"model.layers.
|
| 42 |
-
"model.layers.
|
| 43 |
-
"model.layers.
|
| 44 |
-
"model.layers.
|
| 45 |
-
"model.layers.
|
| 46 |
-
"model.layers.
|
| 47 |
-
"model.layers.
|
| 48 |
-
"model.layers.
|
| 49 |
-
"model.layers.
|
| 50 |
-
"model.layers.
|
| 51 |
-
"model.layers.
|
| 52 |
-
"model.layers.
|
| 53 |
-
"model.layers.
|
| 54 |
-
"model.layers.
|
| 55 |
-
"model.layers.
|
| 56 |
-
"model.layers.
|
| 57 |
-
"model.layers.
|
| 58 |
-
"model.layers.
|
| 59 |
-
"model.layers.
|
| 60 |
-
"model.layers.
|
| 61 |
-
"model.layers.
|
| 62 |
-
"model.layers.
|
| 63 |
-
"model.layers.
|
| 64 |
-
"model.layers.
|
| 65 |
-
"model.layers.
|
| 66 |
-
"model.layers.
|
| 67 |
-
"model.layers.
|
| 68 |
-
"model.layers.
|
| 69 |
-
"model.layers.
|
| 70 |
-
"model.layers.
|
| 71 |
-
"model.layers.
|
| 72 |
-
"model.layers.
|
| 73 |
-
"model.layers.
|
| 74 |
-
"model.layers.
|
| 75 |
-
"model.layers.
|
| 76 |
-
"model.layers.
|
| 77 |
-
"model.layers.
|
| 78 |
-
"model.layers.
|
| 79 |
-
"model.layers.
|
| 80 |
-
"model.layers.
|
| 81 |
-
"model.layers.
|
| 82 |
-
"model.layers.
|
| 83 |
-
"model.layers.
|
| 84 |
-
"model.layers.
|
| 85 |
-
"model.layers.
|
| 86 |
-
"model.layers.
|
| 87 |
-
"model.layers.
|
| 88 |
-
"model.layers.
|
| 89 |
-
"model.layers.
|
| 90 |
-
"model.layers.
|
| 91 |
-
"model.layers.
|
| 92 |
-
"model.layers.
|
| 93 |
-
"model.layers.
|
| 94 |
-
"model.layers.
|
| 95 |
-
"model.layers.
|
| 96 |
-
"model.layers.
|
| 97 |
-
"model.layers.
|
| 98 |
-
"model.layers.
|
| 99 |
-
"model.layers.
|
| 100 |
-
"model.layers.
|
| 101 |
-
"model.layers.
|
| 102 |
-
"model.layers.
|
| 103 |
-
"model.layers.
|
| 104 |
-
"model.layers.
|
| 105 |
-
"model.layers.
|
| 106 |
-
"model.layers.
|
| 107 |
-
"model.layers.
|
| 108 |
-
"model.layers.
|
| 109 |
-
"model.layers.
|
| 110 |
-
"model.layers.
|
| 111 |
-
"model.layers.
|
| 112 |
-
"model.layers.
|
| 113 |
-
"model.layers.
|
| 114 |
-
"model.layers.
|
| 115 |
-
"model.layers.
|
| 116 |
-
"model.layers.
|
| 117 |
-
"model.layers.
|
| 118 |
-
"model.layers.
|
| 119 |
-
"model.layers.
|
| 120 |
-
"model.layers.
|
| 121 |
-
"model.layers.
|
| 122 |
-
"model.layers.
|
| 123 |
-
"model.layers.
|
| 124 |
-
"model.layers.
|
| 125 |
-
"model.layers.
|
| 126 |
-
"model.layers.
|
| 127 |
-
"model.layers.
|
| 128 |
-
"model.layers.
|
| 129 |
-
"model.layers.
|
| 130 |
-
"model.layers.
|
| 131 |
-
"model.layers.
|
| 132 |
-
"model.layers.
|
| 133 |
-
"model.layers.
|
| 134 |
-
"model.layers.
|
| 135 |
-
"model.layers.
|
| 136 |
-
"model.layers.
|
| 137 |
-
"model.layers.
|
| 138 |
-
"model.layers.
|
| 139 |
-
"model.layers.
|
| 140 |
-
"model.layers.
|
| 141 |
-
"model.layers.
|
| 142 |
-
"model.layers.
|
| 143 |
-
"model.layers.
|
| 144 |
-
"model.layers.
|
| 145 |
-
"model.layers.
|
| 146 |
-
"model.layers.
|
| 147 |
-
"model.layers.
|
| 148 |
-
"model.layers.
|
| 149 |
-
"model.layers.
|
| 150 |
-
"model.layers.
|
| 151 |
-
"model.layers.
|
| 152 |
-
"model.layers.
|
| 153 |
-
"model.layers.
|
| 154 |
-
"model.layers.
|
| 155 |
-
"model.layers.
|
| 156 |
-
"model.layers.
|
| 157 |
-
"model.layers.
|
| 158 |
-
"model.layers.
|
| 159 |
-
"model.layers.
|
| 160 |
-
"model.layers.
|
| 161 |
-
"model.layers.
|
| 162 |
-
"model.layers.
|
| 163 |
-
"model.layers.
|
| 164 |
-
"model.layers.
|
| 165 |
-
"model.layers.
|
| 166 |
-
"model.layers.
|
| 167 |
-
"model.layers.
|
| 168 |
-
"model.layers.
|
| 169 |
-
"model.layers.
|
| 170 |
-
"model.layers.
|
| 171 |
-
"model.layers.
|
| 172 |
-
"model.layers.
|
| 173 |
-
"model.layers.
|
| 174 |
-
"model.layers.
|
| 175 |
-
"model.layers.
|
| 176 |
-
"model.layers.
|
| 177 |
-
"model.layers.
|
| 178 |
-
"model.layers.
|
| 179 |
-
"model.layers.
|
| 180 |
-
"model.layers.
|
| 181 |
-
"model.layers.
|
| 182 |
-
"model.layers.
|
| 183 |
-
"model.layers.
|
| 184 |
-
"model.layers.
|
| 185 |
-
"model.layers.
|
| 186 |
-
"model.layers.
|
| 187 |
-
"model.layers.
|
| 188 |
-
"model.layers.
|
| 189 |
-
"model.layers.
|
| 190 |
-
"model.layers.
|
| 191 |
-
"model.layers.
|
| 192 |
-
"model.layers.
|
| 193 |
-
"model.layers.
|
| 194 |
-
"model.layers.
|
| 195 |
-
"model.layers.
|
| 196 |
-
"model.layers.
|
| 197 |
-
"model.layers.
|
| 198 |
-
"model.layers.
|
| 199 |
-
"model.layers.
|
| 200 |
-
"model.layers.
|
| 201 |
-
"model.layers.
|
| 202 |
-
"model.layers.
|
| 203 |
-
"model.layers.
|
| 204 |
-
"model.layers.
|
| 205 |
-
"model.layers.
|
| 206 |
-
"model.layers.
|
| 207 |
-
"model.layers.
|
| 208 |
-
"model.layers.
|
| 209 |
-
"model.layers.
|
| 210 |
-
"model.layers.
|
| 211 |
-
"model.layers.
|
| 212 |
-
"model.layers.
|
| 213 |
-
"model.layers.
|
| 214 |
-
"model.layers.
|
| 215 |
-
"model.layers.
|
| 216 |
-
"model.layers.
|
| 217 |
-
"model.layers.
|
| 218 |
-
"model.layers.
|
| 219 |
-
"model.layers.
|
| 220 |
-
"model.layers.
|
| 221 |
-
"model.layers.
|
| 222 |
-
"model.layers.
|
| 223 |
-
"model.layers.
|
| 224 |
-
"model.layers.
|
| 225 |
-
"model.layers.
|
| 226 |
-
"model.layers.
|
| 227 |
-
"model.layers.
|
| 228 |
-
"model.layers.
|
| 229 |
-
"model.layers.
|
| 230 |
-
"model.layers.
|
| 231 |
-
"model.layers.
|
| 232 |
-
"model.layers.
|
| 233 |
-
"model.layers.
|
| 234 |
-
"model.layers.
|
| 235 |
-
"model.layers.
|
| 236 |
-
"model.layers.
|
| 237 |
-
"model.layers.
|
| 238 |
-
"model.layers.
|
| 239 |
-
"model.layers.
|
| 240 |
-
"model.layers.
|
| 241 |
-
"model.layers.
|
| 242 |
-
"model.layers.
|
| 243 |
-
"model.layers.
|
| 244 |
-
"model.layers.
|
| 245 |
-
"model.layers.
|
| 246 |
-
"model.layers.
|
| 247 |
-
"model.layers.
|
| 248 |
-
"model.layers.
|
| 249 |
-
"model.layers.
|
| 250 |
-
"model.layers.
|
| 251 |
-
"model.layers.
|
| 252 |
-
"model.layers.
|
| 253 |
-
"model.layers.
|
| 254 |
-
"model.layers.
|
| 255 |
-
"model.layers.
|
| 256 |
-
"model.layers.
|
| 257 |
-
"model.layers.
|
| 258 |
-
"model.layers.
|
| 259 |
-
"model.layers.
|
| 260 |
-
"model.layers.
|
| 261 |
-
"model.layers.
|
| 262 |
-
"model.layers.
|
| 263 |
-
"model.layers.
|
| 264 |
-
"model.layers.
|
| 265 |
-
"model.layers.
|
| 266 |
-
"model.layers.
|
| 267 |
-
"model.layers.
|
| 268 |
-
"model.layers.
|
| 269 |
-
"model.layers.
|
| 270 |
-
"model.layers.
|
| 271 |
-
"model.layers.
|
| 272 |
-
"model.layers.
|
| 273 |
-
"model.layers.
|
| 274 |
-
"model.layers.
|
| 275 |
-
"model.layers.
|
| 276 |
-
"model.layers.
|
| 277 |
-
"model.layers.
|
| 278 |
-
"model.layers.
|
| 279 |
-
"model.layers.
|
| 280 |
-
"model.layers.
|
| 281 |
-
"model.layers.
|
| 282 |
-
"model.layers.
|
| 283 |
-
"model.layers.
|
| 284 |
-
"model.layers.
|
| 285 |
-
"model.layers.
|
| 286 |
-
"model.layers.
|
| 287 |
-
"model.layers.
|
| 288 |
-
"model.layers.
|
| 289 |
-
"model.layers.
|
| 290 |
-
"model.layers.
|
| 291 |
-
"model.layers.
|
| 292 |
-
"model.layers.
|
| 293 |
-
"model.layers.
|
| 294 |
-
"model.layers.
|
| 295 |
-
"model.layers.
|
| 296 |
-
"model.
|
| 297 |
-
"model.layers.2.self_attn.k_proj.biases": "model.safetensors",
|
| 298 |
-
"model.layers.2.self_attn.k_proj.scales": "model.safetensors",
|
| 299 |
-
"model.layers.2.self_attn.k_proj.weight": "model.safetensors",
|
| 300 |
-
"model.layers.2.self_attn.o_proj.biases": "model.safetensors",
|
| 301 |
-
"model.layers.2.self_attn.o_proj.scales": "model.safetensors",
|
| 302 |
-
"model.layers.2.self_attn.o_proj.weight": "model.safetensors",
|
| 303 |
-
"model.layers.2.self_attn.q_proj.biases": "model.safetensors",
|
| 304 |
-
"model.layers.2.self_attn.q_proj.scales": "model.safetensors",
|
| 305 |
-
"model.layers.2.self_attn.q_proj.weight": "model.safetensors",
|
| 306 |
-
"model.layers.2.self_attn.v_proj.biases": "model.safetensors",
|
| 307 |
-
"model.layers.2.self_attn.v_proj.scales": "model.safetensors",
|
| 308 |
-
"model.layers.2.self_attn.v_proj.weight": "model.safetensors",
|
| 309 |
-
"model.layers.20.input_layernorm.weight": "model.safetensors",
|
| 310 |
-
"model.layers.20.mlp.down_proj.biases": "model.safetensors",
|
| 311 |
-
"model.layers.20.mlp.down_proj.scales": "model.safetensors",
|
| 312 |
-
"model.layers.20.mlp.down_proj.weight": "model.safetensors",
|
| 313 |
-
"model.layers.20.mlp.gate_proj.biases": "model.safetensors",
|
| 314 |
-
"model.layers.20.mlp.gate_proj.scales": "model.safetensors",
|
| 315 |
-
"model.layers.20.mlp.gate_proj.weight": "model.safetensors",
|
| 316 |
-
"model.layers.20.mlp.up_proj.biases": "model.safetensors",
|
| 317 |
-
"model.layers.20.mlp.up_proj.scales": "model.safetensors",
|
| 318 |
-
"model.layers.20.mlp.up_proj.weight": "model.safetensors",
|
| 319 |
-
"model.layers.20.post_attention_layernorm.weight": "model.safetensors",
|
| 320 |
-
"model.layers.20.self_attn.k_proj.biases": "model.safetensors",
|
| 321 |
-
"model.layers.20.self_attn.k_proj.scales": "model.safetensors",
|
| 322 |
-
"model.layers.20.self_attn.k_proj.weight": "model.safetensors",
|
| 323 |
-
"model.layers.20.self_attn.o_proj.biases": "model.safetensors",
|
| 324 |
-
"model.layers.20.self_attn.o_proj.scales": "model.safetensors",
|
| 325 |
-
"model.layers.20.self_attn.o_proj.weight": "model.safetensors",
|
| 326 |
-
"model.layers.20.self_attn.q_proj.biases": "model.safetensors",
|
| 327 |
-
"model.layers.20.self_attn.q_proj.scales": "model.safetensors",
|
| 328 |
-
"model.layers.20.self_attn.q_proj.weight": "model.safetensors",
|
| 329 |
-
"model.layers.20.self_attn.v_proj.biases": "model.safetensors",
|
| 330 |
-
"model.layers.20.self_attn.v_proj.scales": "model.safetensors",
|
| 331 |
-
"model.layers.20.self_attn.v_proj.weight": "model.safetensors",
|
| 332 |
-
"model.layers.21.input_layernorm.weight": "model.safetensors",
|
| 333 |
-
"model.layers.21.mlp.down_proj.biases": "model.safetensors",
|
| 334 |
-
"model.layers.21.mlp.down_proj.scales": "model.safetensors",
|
| 335 |
-
"model.layers.21.mlp.down_proj.weight": "model.safetensors",
|
| 336 |
-
"model.layers.21.mlp.gate_proj.biases": "model.safetensors",
|
| 337 |
-
"model.layers.21.mlp.gate_proj.scales": "model.safetensors",
|
| 338 |
-
"model.layers.21.mlp.gate_proj.weight": "model.safetensors",
|
| 339 |
-
"model.layers.21.mlp.up_proj.biases": "model.safetensors",
|
| 340 |
-
"model.layers.21.mlp.up_proj.scales": "model.safetensors",
|
| 341 |
-
"model.layers.21.mlp.up_proj.weight": "model.safetensors",
|
| 342 |
-
"model.layers.21.post_attention_layernorm.weight": "model.safetensors",
|
| 343 |
-
"model.layers.21.self_attn.k_proj.biases": "model.safetensors",
|
| 344 |
-
"model.layers.21.self_attn.k_proj.scales": "model.safetensors",
|
| 345 |
-
"model.layers.21.self_attn.k_proj.weight": "model.safetensors",
|
| 346 |
-
"model.layers.21.self_attn.o_proj.biases": "model.safetensors",
|
| 347 |
-
"model.layers.21.self_attn.o_proj.scales": "model.safetensors",
|
| 348 |
-
"model.layers.21.self_attn.o_proj.weight": "model.safetensors",
|
| 349 |
-
"model.layers.21.self_attn.q_proj.biases": "model.safetensors",
|
| 350 |
-
"model.layers.21.self_attn.q_proj.scales": "model.safetensors",
|
| 351 |
-
"model.layers.21.self_attn.q_proj.weight": "model.safetensors",
|
| 352 |
-
"model.layers.21.self_attn.v_proj.biases": "model.safetensors",
|
| 353 |
-
"model.layers.21.self_attn.v_proj.scales": "model.safetensors",
|
| 354 |
-
"model.layers.21.self_attn.v_proj.weight": "model.safetensors",
|
| 355 |
-
"model.layers.22.input_layernorm.weight": "model.safetensors",
|
| 356 |
-
"model.layers.22.mlp.down_proj.biases": "model.safetensors",
|
| 357 |
-
"model.layers.22.mlp.down_proj.scales": "model.safetensors",
|
| 358 |
-
"model.layers.22.mlp.down_proj.weight": "model.safetensors",
|
| 359 |
-
"model.layers.22.mlp.gate_proj.biases": "model.safetensors",
|
| 360 |
-
"model.layers.22.mlp.gate_proj.scales": "model.safetensors",
|
| 361 |
-
"model.layers.22.mlp.gate_proj.weight": "model.safetensors",
|
| 362 |
-
"model.layers.22.mlp.up_proj.biases": "model.safetensors",
|
| 363 |
-
"model.layers.22.mlp.up_proj.scales": "model.safetensors",
|
| 364 |
-
"model.layers.22.mlp.up_proj.weight": "model.safetensors",
|
| 365 |
-
"model.layers.22.post_attention_layernorm.weight": "model.safetensors",
|
| 366 |
-
"model.layers.22.self_attn.k_proj.biases": "model.safetensors",
|
| 367 |
-
"model.layers.22.self_attn.k_proj.scales": "model.safetensors",
|
| 368 |
-
"model.layers.22.self_attn.k_proj.weight": "model.safetensors",
|
| 369 |
-
"model.layers.22.self_attn.o_proj.biases": "model.safetensors",
|
| 370 |
-
"model.layers.22.self_attn.o_proj.scales": "model.safetensors",
|
| 371 |
-
"model.layers.22.self_attn.o_proj.weight": "model.safetensors",
|
| 372 |
-
"model.layers.22.self_attn.q_proj.biases": "model.safetensors",
|
| 373 |
-
"model.layers.22.self_attn.q_proj.scales": "model.safetensors",
|
| 374 |
-
"model.layers.22.self_attn.q_proj.weight": "model.safetensors",
|
| 375 |
-
"model.layers.22.self_attn.v_proj.biases": "model.safetensors",
|
| 376 |
-
"model.layers.22.self_attn.v_proj.scales": "model.safetensors",
|
| 377 |
-
"model.layers.22.self_attn.v_proj.weight": "model.safetensors",
|
| 378 |
-
"model.layers.23.input_layernorm.weight": "model.safetensors",
|
| 379 |
-
"model.layers.23.mlp.down_proj.biases": "model.safetensors",
|
| 380 |
-
"model.layers.23.mlp.down_proj.scales": "model.safetensors",
|
| 381 |
-
"model.layers.23.mlp.down_proj.weight": "model.safetensors",
|
| 382 |
-
"model.layers.23.mlp.gate_proj.biases": "model.safetensors",
|
| 383 |
-
"model.layers.23.mlp.gate_proj.scales": "model.safetensors",
|
| 384 |
-
"model.layers.23.mlp.gate_proj.weight": "model.safetensors",
|
| 385 |
-
"model.layers.23.mlp.up_proj.biases": "model.safetensors",
|
| 386 |
-
"model.layers.23.mlp.up_proj.scales": "model.safetensors",
|
| 387 |
-
"model.layers.23.mlp.up_proj.weight": "model.safetensors",
|
| 388 |
-
"model.layers.23.post_attention_layernorm.weight": "model.safetensors",
|
| 389 |
-
"model.layers.23.self_attn.k_proj.biases": "model.safetensors",
|
| 390 |
-
"model.layers.23.self_attn.k_proj.scales": "model.safetensors",
|
| 391 |
-
"model.layers.23.self_attn.k_proj.weight": "model.safetensors",
|
| 392 |
-
"model.layers.23.self_attn.o_proj.biases": "model.safetensors",
|
| 393 |
-
"model.layers.23.self_attn.o_proj.scales": "model.safetensors",
|
| 394 |
-
"model.layers.23.self_attn.o_proj.weight": "model.safetensors",
|
| 395 |
-
"model.layers.23.self_attn.q_proj.biases": "model.safetensors",
|
| 396 |
-
"model.layers.23.self_attn.q_proj.scales": "model.safetensors",
|
| 397 |
-
"model.layers.23.self_attn.q_proj.weight": "model.safetensors",
|
| 398 |
-
"model.layers.23.self_attn.v_proj.biases": "model.safetensors",
|
| 399 |
-
"model.layers.23.self_attn.v_proj.scales": "model.safetensors",
|
| 400 |
-
"model.layers.23.self_attn.v_proj.weight": "model.safetensors",
|
| 401 |
-
"model.layers.24.input_layernorm.weight": "model.safetensors",
|
| 402 |
-
"model.layers.24.mlp.down_proj.biases": "model.safetensors",
|
| 403 |
-
"model.layers.24.mlp.down_proj.scales": "model.safetensors",
|
| 404 |
-
"model.layers.24.mlp.down_proj.weight": "model.safetensors",
|
| 405 |
-
"model.layers.24.mlp.gate_proj.biases": "model.safetensors",
|
| 406 |
-
"model.layers.24.mlp.gate_proj.scales": "model.safetensors",
|
| 407 |
-
"model.layers.24.mlp.gate_proj.weight": "model.safetensors",
|
| 408 |
-
"model.layers.24.mlp.up_proj.biases": "model.safetensors",
|
| 409 |
-
"model.layers.24.mlp.up_proj.scales": "model.safetensors",
|
| 410 |
-
"model.layers.24.mlp.up_proj.weight": "model.safetensors",
|
| 411 |
-
"model.layers.24.post_attention_layernorm.weight": "model.safetensors",
|
| 412 |
-
"model.layers.24.self_attn.k_proj.biases": "model.safetensors",
|
| 413 |
-
"model.layers.24.self_attn.k_proj.scales": "model.safetensors",
|
| 414 |
-
"model.layers.24.self_attn.k_proj.weight": "model.safetensors",
|
| 415 |
-
"model.layers.24.self_attn.o_proj.biases": "model.safetensors",
|
| 416 |
-
"model.layers.24.self_attn.o_proj.scales": "model.safetensors",
|
| 417 |
-
"model.layers.24.self_attn.o_proj.weight": "model.safetensors",
|
| 418 |
-
"model.layers.24.self_attn.q_proj.biases": "model.safetensors",
|
| 419 |
-
"model.layers.24.self_attn.q_proj.scales": "model.safetensors",
|
| 420 |
-
"model.layers.24.self_attn.q_proj.weight": "model.safetensors",
|
| 421 |
-
"model.layers.24.self_attn.v_proj.biases": "model.safetensors",
|
| 422 |
-
"model.layers.24.self_attn.v_proj.scales": "model.safetensors",
|
| 423 |
-
"model.layers.24.self_attn.v_proj.weight": "model.safetensors",
|
| 424 |
-
"model.layers.25.input_layernorm.weight": "model.safetensors",
|
| 425 |
-
"model.layers.25.mlp.down_proj.biases": "model.safetensors",
|
| 426 |
-
"model.layers.25.mlp.down_proj.scales": "model.safetensors",
|
| 427 |
-
"model.layers.25.mlp.down_proj.weight": "model.safetensors",
|
| 428 |
-
"model.layers.25.mlp.gate_proj.biases": "model.safetensors",
|
| 429 |
-
"model.layers.25.mlp.gate_proj.scales": "model.safetensors",
|
| 430 |
-
"model.layers.25.mlp.gate_proj.weight": "model.safetensors",
|
| 431 |
-
"model.layers.25.mlp.up_proj.biases": "model.safetensors",
|
| 432 |
-
"model.layers.25.mlp.up_proj.scales": "model.safetensors",
|
| 433 |
-
"model.layers.25.mlp.up_proj.weight": "model.safetensors",
|
| 434 |
-
"model.layers.25.post_attention_layernorm.weight": "model.safetensors",
|
| 435 |
-
"model.layers.25.self_attn.k_proj.biases": "model.safetensors",
|
| 436 |
-
"model.layers.25.self_attn.k_proj.scales": "model.safetensors",
|
| 437 |
-
"model.layers.25.self_attn.k_proj.weight": "model.safetensors",
|
| 438 |
-
"model.layers.25.self_attn.o_proj.biases": "model.safetensors",
|
| 439 |
-
"model.layers.25.self_attn.o_proj.scales": "model.safetensors",
|
| 440 |
-
"model.layers.25.self_attn.o_proj.weight": "model.safetensors",
|
| 441 |
-
"model.layers.25.self_attn.q_proj.biases": "model.safetensors",
|
| 442 |
-
"model.layers.25.self_attn.q_proj.scales": "model.safetensors",
|
| 443 |
-
"model.layers.25.self_attn.q_proj.weight": "model.safetensors",
|
| 444 |
-
"model.layers.25.self_attn.v_proj.biases": "model.safetensors",
|
| 445 |
-
"model.layers.25.self_attn.v_proj.scales": "model.safetensors",
|
| 446 |
-
"model.layers.25.self_attn.v_proj.weight": "model.safetensors",
|
| 447 |
-
"model.layers.26.input_layernorm.weight": "model.safetensors",
|
| 448 |
-
"model.layers.26.mlp.down_proj.biases": "model.safetensors",
|
| 449 |
-
"model.layers.26.mlp.down_proj.scales": "model.safetensors",
|
| 450 |
-
"model.layers.26.mlp.down_proj.weight": "model.safetensors",
|
| 451 |
-
"model.layers.26.mlp.gate_proj.biases": "model.safetensors",
|
| 452 |
-
"model.layers.26.mlp.gate_proj.scales": "model.safetensors",
|
| 453 |
-
"model.layers.26.mlp.gate_proj.weight": "model.safetensors",
|
| 454 |
-
"model.layers.26.mlp.up_proj.biases": "model.safetensors",
|
| 455 |
-
"model.layers.26.mlp.up_proj.scales": "model.safetensors",
|
| 456 |
-
"model.layers.26.mlp.up_proj.weight": "model.safetensors",
|
| 457 |
-
"model.layers.26.post_attention_layernorm.weight": "model.safetensors",
|
| 458 |
-
"model.layers.26.self_attn.k_proj.biases": "model.safetensors",
|
| 459 |
-
"model.layers.26.self_attn.k_proj.scales": "model.safetensors",
|
| 460 |
-
"model.layers.26.self_attn.k_proj.weight": "model.safetensors",
|
| 461 |
-
"model.layers.26.self_attn.o_proj.biases": "model.safetensors",
|
| 462 |
-
"model.layers.26.self_attn.o_proj.scales": "model.safetensors",
|
| 463 |
-
"model.layers.26.self_attn.o_proj.weight": "model.safetensors",
|
| 464 |
-
"model.layers.26.self_attn.q_proj.biases": "model.safetensors",
|
| 465 |
-
"model.layers.26.self_attn.q_proj.scales": "model.safetensors",
|
| 466 |
-
"model.layers.26.self_attn.q_proj.weight": "model.safetensors",
|
| 467 |
-
"model.layers.26.self_attn.v_proj.biases": "model.safetensors",
|
| 468 |
-
"model.layers.26.self_attn.v_proj.scales": "model.safetensors",
|
| 469 |
-
"model.layers.26.self_attn.v_proj.weight": "model.safetensors",
|
| 470 |
-
"model.layers.27.input_layernorm.weight": "model.safetensors",
|
| 471 |
-
"model.layers.27.mlp.down_proj.biases": "model.safetensors",
|
| 472 |
-
"model.layers.27.mlp.down_proj.scales": "model.safetensors",
|
| 473 |
-
"model.layers.27.mlp.down_proj.weight": "model.safetensors",
|
| 474 |
-
"model.layers.27.mlp.gate_proj.biases": "model.safetensors",
|
| 475 |
-
"model.layers.27.mlp.gate_proj.scales": "model.safetensors",
|
| 476 |
-
"model.layers.27.mlp.gate_proj.weight": "model.safetensors",
|
| 477 |
-
"model.layers.27.mlp.up_proj.biases": "model.safetensors",
|
| 478 |
-
"model.layers.27.mlp.up_proj.scales": "model.safetensors",
|
| 479 |
-
"model.layers.27.mlp.up_proj.weight": "model.safetensors",
|
| 480 |
-
"model.layers.27.post_attention_layernorm.weight": "model.safetensors",
|
| 481 |
-
"model.layers.27.self_attn.k_proj.biases": "model.safetensors",
|
| 482 |
-
"model.layers.27.self_attn.k_proj.scales": "model.safetensors",
|
| 483 |
-
"model.layers.27.self_attn.k_proj.weight": "model.safetensors",
|
| 484 |
-
"model.layers.27.self_attn.o_proj.biases": "model.safetensors",
|
| 485 |
-
"model.layers.27.self_attn.o_proj.scales": "model.safetensors",
|
| 486 |
-
"model.layers.27.self_attn.o_proj.weight": "model.safetensors",
|
| 487 |
-
"model.layers.27.self_attn.q_proj.biases": "model.safetensors",
|
| 488 |
-
"model.layers.27.self_attn.q_proj.scales": "model.safetensors",
|
| 489 |
-
"model.layers.27.self_attn.q_proj.weight": "model.safetensors",
|
| 490 |
-
"model.layers.27.self_attn.v_proj.biases": "model.safetensors",
|
| 491 |
-
"model.layers.27.self_attn.v_proj.scales": "model.safetensors",
|
| 492 |
-
"model.layers.27.self_attn.v_proj.weight": "model.safetensors",
|
| 493 |
-
"model.layers.28.input_layernorm.weight": "model.safetensors",
|
| 494 |
-
"model.layers.28.mlp.down_proj.biases": "model.safetensors",
|
| 495 |
-
"model.layers.28.mlp.down_proj.scales": "model.safetensors",
|
| 496 |
-
"model.layers.28.mlp.down_proj.weight": "model.safetensors",
|
| 497 |
-
"model.layers.28.mlp.gate_proj.biases": "model.safetensors",
|
| 498 |
-
"model.layers.28.mlp.gate_proj.scales": "model.safetensors",
|
| 499 |
-
"model.layers.28.mlp.gate_proj.weight": "model.safetensors",
|
| 500 |
-
"model.layers.28.mlp.up_proj.biases": "model.safetensors",
|
| 501 |
-
"model.layers.28.mlp.up_proj.scales": "model.safetensors",
|
| 502 |
-
"model.layers.28.mlp.up_proj.weight": "model.safetensors",
|
| 503 |
-
"model.layers.28.post_attention_layernorm.weight": "model.safetensors",
|
| 504 |
-
"model.layers.28.self_attn.k_proj.biases": "model.safetensors",
|
| 505 |
-
"model.layers.28.self_attn.k_proj.scales": "model.safetensors",
|
| 506 |
-
"model.layers.28.self_attn.k_proj.weight": "model.safetensors",
|
| 507 |
-
"model.layers.28.self_attn.o_proj.biases": "model.safetensors",
|
| 508 |
-
"model.layers.28.self_attn.o_proj.scales": "model.safetensors",
|
| 509 |
-
"model.layers.28.self_attn.o_proj.weight": "model.safetensors",
|
| 510 |
-
"model.layers.28.self_attn.q_proj.biases": "model.safetensors",
|
| 511 |
-
"model.layers.28.self_attn.q_proj.scales": "model.safetensors",
|
| 512 |
-
"model.layers.28.self_attn.q_proj.weight": "model.safetensors",
|
| 513 |
-
"model.layers.28.self_attn.v_proj.biases": "model.safetensors",
|
| 514 |
-
"model.layers.28.self_attn.v_proj.scales": "model.safetensors",
|
| 515 |
-
"model.layers.28.self_attn.v_proj.weight": "model.safetensors",
|
| 516 |
-
"model.layers.29.input_layernorm.weight": "model.safetensors",
|
| 517 |
-
"model.layers.29.mlp.down_proj.biases": "model.safetensors",
|
| 518 |
-
"model.layers.29.mlp.down_proj.scales": "model.safetensors",
|
| 519 |
-
"model.layers.29.mlp.down_proj.weight": "model.safetensors",
|
| 520 |
-
"model.layers.29.mlp.gate_proj.biases": "model.safetensors",
|
| 521 |
-
"model.layers.29.mlp.gate_proj.scales": "model.safetensors",
|
| 522 |
-
"model.layers.29.mlp.gate_proj.weight": "model.safetensors",
|
| 523 |
-
"model.layers.29.mlp.up_proj.biases": "model.safetensors",
|
| 524 |
-
"model.layers.29.mlp.up_proj.scales": "model.safetensors",
|
| 525 |
-
"model.layers.29.mlp.up_proj.weight": "model.safetensors",
|
| 526 |
-
"model.layers.29.post_attention_layernorm.weight": "model.safetensors",
|
| 527 |
-
"model.layers.29.self_attn.k_proj.biases": "model.safetensors",
|
| 528 |
-
"model.layers.29.self_attn.k_proj.scales": "model.safetensors",
|
| 529 |
-
"model.layers.29.self_attn.k_proj.weight": "model.safetensors",
|
| 530 |
-
"model.layers.29.self_attn.o_proj.biases": "model.safetensors",
|
| 531 |
-
"model.layers.29.self_attn.o_proj.scales": "model.safetensors",
|
| 532 |
-
"model.layers.29.self_attn.o_proj.weight": "model.safetensors",
|
| 533 |
-
"model.layers.29.self_attn.q_proj.biases": "model.safetensors",
|
| 534 |
-
"model.layers.29.self_attn.q_proj.scales": "model.safetensors",
|
| 535 |
-
"model.layers.29.self_attn.q_proj.weight": "model.safetensors",
|
| 536 |
-
"model.layers.29.self_attn.v_proj.biases": "model.safetensors",
|
| 537 |
-
"model.layers.29.self_attn.v_proj.scales": "model.safetensors",
|
| 538 |
-
"model.layers.29.self_attn.v_proj.weight": "model.safetensors",
|
| 539 |
-
"model.layers.3.input_layernorm.weight": "model.safetensors",
|
| 540 |
-
"model.layers.3.mlp.down_proj.biases": "model.safetensors",
|
| 541 |
-
"model.layers.3.mlp.down_proj.scales": "model.safetensors",
|
| 542 |
-
"model.layers.3.mlp.down_proj.weight": "model.safetensors",
|
| 543 |
-
"model.layers.3.mlp.gate_proj.biases": "model.safetensors",
|
| 544 |
-
"model.layers.3.mlp.gate_proj.scales": "model.safetensors",
|
| 545 |
-
"model.layers.3.mlp.gate_proj.weight": "model.safetensors",
|
| 546 |
-
"model.layers.3.mlp.up_proj.biases": "model.safetensors",
|
| 547 |
-
"model.layers.3.mlp.up_proj.scales": "model.safetensors",
|
| 548 |
-
"model.layers.3.mlp.up_proj.weight": "model.safetensors",
|
| 549 |
-
"model.layers.3.post_attention_layernorm.weight": "model.safetensors",
|
| 550 |
-
"model.layers.3.self_attn.k_proj.biases": "model.safetensors",
|
| 551 |
-
"model.layers.3.self_attn.k_proj.scales": "model.safetensors",
|
| 552 |
-
"model.layers.3.self_attn.k_proj.weight": "model.safetensors",
|
| 553 |
-
"model.layers.3.self_attn.o_proj.biases": "model.safetensors",
|
| 554 |
-
"model.layers.3.self_attn.o_proj.scales": "model.safetensors",
|
| 555 |
-
"model.layers.3.self_attn.o_proj.weight": "model.safetensors",
|
| 556 |
-
"model.layers.3.self_attn.q_proj.biases": "model.safetensors",
|
| 557 |
-
"model.layers.3.self_attn.q_proj.scales": "model.safetensors",
|
| 558 |
-
"model.layers.3.self_attn.q_proj.weight": "model.safetensors",
|
| 559 |
-
"model.layers.3.self_attn.v_proj.biases": "model.safetensors",
|
| 560 |
-
"model.layers.3.self_attn.v_proj.scales": "model.safetensors",
|
| 561 |
-
"model.layers.3.self_attn.v_proj.weight": "model.safetensors",
|
| 562 |
-
"model.layers.30.input_layernorm.weight": "model.safetensors",
|
| 563 |
-
"model.layers.30.mlp.down_proj.biases": "model.safetensors",
|
| 564 |
-
"model.layers.30.mlp.down_proj.scales": "model.safetensors",
|
| 565 |
-
"model.layers.30.mlp.down_proj.weight": "model.safetensors",
|
| 566 |
-
"model.layers.30.mlp.gate_proj.biases": "model.safetensors",
|
| 567 |
-
"model.layers.30.mlp.gate_proj.scales": "model.safetensors",
|
| 568 |
-
"model.layers.30.mlp.gate_proj.weight": "model.safetensors",
|
| 569 |
-
"model.layers.30.mlp.up_proj.biases": "model.safetensors",
|
| 570 |
-
"model.layers.30.mlp.up_proj.scales": "model.safetensors",
|
| 571 |
-
"model.layers.30.mlp.up_proj.weight": "model.safetensors",
|
| 572 |
-
"model.layers.30.post_attention_layernorm.weight": "model.safetensors",
|
| 573 |
-
"model.layers.30.self_attn.k_proj.biases": "model.safetensors",
|
| 574 |
-
"model.layers.30.self_attn.k_proj.scales": "model.safetensors",
|
| 575 |
-
"model.layers.30.self_attn.k_proj.weight": "model.safetensors",
|
| 576 |
-
"model.layers.30.self_attn.o_proj.biases": "model.safetensors",
|
| 577 |
-
"model.layers.30.self_attn.o_proj.scales": "model.safetensors",
|
| 578 |
-
"model.layers.30.self_attn.o_proj.weight": "model.safetensors",
|
| 579 |
-
"model.layers.30.self_attn.q_proj.biases": "model.safetensors",
|
| 580 |
-
"model.layers.30.self_attn.q_proj.scales": "model.safetensors",
|
| 581 |
-
"model.layers.30.self_attn.q_proj.weight": "model.safetensors",
|
| 582 |
-
"model.layers.30.self_attn.v_proj.biases": "model.safetensors",
|
| 583 |
-
"model.layers.30.self_attn.v_proj.scales": "model.safetensors",
|
| 584 |
-
"model.layers.30.self_attn.v_proj.weight": "model.safetensors",
|
| 585 |
-
"model.layers.31.input_layernorm.weight": "model.safetensors",
|
| 586 |
-
"model.layers.31.mlp.down_proj.biases": "model.safetensors",
|
| 587 |
-
"model.layers.31.mlp.down_proj.scales": "model.safetensors",
|
| 588 |
-
"model.layers.31.mlp.down_proj.weight": "model.safetensors",
|
| 589 |
-
"model.layers.31.mlp.gate_proj.biases": "model.safetensors",
|
| 590 |
-
"model.layers.31.mlp.gate_proj.scales": "model.safetensors",
|
| 591 |
-
"model.layers.31.mlp.gate_proj.weight": "model.safetensors",
|
| 592 |
-
"model.layers.31.mlp.up_proj.biases": "model.safetensors",
|
| 593 |
-
"model.layers.31.mlp.up_proj.scales": "model.safetensors",
|
| 594 |
-
"model.layers.31.mlp.up_proj.weight": "model.safetensors",
|
| 595 |
-
"model.layers.31.post_attention_layernorm.weight": "model.safetensors",
|
| 596 |
-
"model.layers.31.self_attn.k_proj.biases": "model.safetensors",
|
| 597 |
-
"model.layers.31.self_attn.k_proj.scales": "model.safetensors",
|
| 598 |
-
"model.layers.31.self_attn.k_proj.weight": "model.safetensors",
|
| 599 |
-
"model.layers.31.self_attn.o_proj.biases": "model.safetensors",
|
| 600 |
-
"model.layers.31.self_attn.o_proj.scales": "model.safetensors",
|
| 601 |
-
"model.layers.31.self_attn.o_proj.weight": "model.safetensors",
|
| 602 |
-
"model.layers.31.self_attn.q_proj.biases": "model.safetensors",
|
| 603 |
-
"model.layers.31.self_attn.q_proj.scales": "model.safetensors",
|
| 604 |
-
"model.layers.31.self_attn.q_proj.weight": "model.safetensors",
|
| 605 |
-
"model.layers.31.self_attn.v_proj.biases": "model.safetensors",
|
| 606 |
-
"model.layers.31.self_attn.v_proj.scales": "model.safetensors",
|
| 607 |
-
"model.layers.31.self_attn.v_proj.weight": "model.safetensors",
|
| 608 |
-
"model.layers.4.input_layernorm.weight": "model.safetensors",
|
| 609 |
-
"model.layers.4.mlp.down_proj.biases": "model.safetensors",
|
| 610 |
-
"model.layers.4.mlp.down_proj.scales": "model.safetensors",
|
| 611 |
-
"model.layers.4.mlp.down_proj.weight": "model.safetensors",
|
| 612 |
-
"model.layers.4.mlp.gate_proj.biases": "model.safetensors",
|
| 613 |
-
"model.layers.4.mlp.gate_proj.scales": "model.safetensors",
|
| 614 |
-
"model.layers.4.mlp.gate_proj.weight": "model.safetensors",
|
| 615 |
-
"model.layers.4.mlp.up_proj.biases": "model.safetensors",
|
| 616 |
-
"model.layers.4.mlp.up_proj.scales": "model.safetensors",
|
| 617 |
-
"model.layers.4.mlp.up_proj.weight": "model.safetensors",
|
| 618 |
-
"model.layers.4.post_attention_layernorm.weight": "model.safetensors",
|
| 619 |
-
"model.layers.4.self_attn.k_proj.biases": "model.safetensors",
|
| 620 |
-
"model.layers.4.self_attn.k_proj.scales": "model.safetensors",
|
| 621 |
-
"model.layers.4.self_attn.k_proj.weight": "model.safetensors",
|
| 622 |
-
"model.layers.4.self_attn.o_proj.biases": "model.safetensors",
|
| 623 |
-
"model.layers.4.self_attn.o_proj.scales": "model.safetensors",
|
| 624 |
-
"model.layers.4.self_attn.o_proj.weight": "model.safetensors",
|
| 625 |
-
"model.layers.4.self_attn.q_proj.biases": "model.safetensors",
|
| 626 |
-
"model.layers.4.self_attn.q_proj.scales": "model.safetensors",
|
| 627 |
-
"model.layers.4.self_attn.q_proj.weight": "model.safetensors",
|
| 628 |
-
"model.layers.4.self_attn.v_proj.biases": "model.safetensors",
|
| 629 |
-
"model.layers.4.self_attn.v_proj.scales": "model.safetensors",
|
| 630 |
-
"model.layers.4.self_attn.v_proj.weight": "model.safetensors",
|
| 631 |
-
"model.layers.5.input_layernorm.weight": "model.safetensors",
|
| 632 |
-
"model.layers.5.mlp.down_proj.biases": "model.safetensors",
|
| 633 |
-
"model.layers.5.mlp.down_proj.scales": "model.safetensors",
|
| 634 |
-
"model.layers.5.mlp.down_proj.weight": "model.safetensors",
|
| 635 |
-
"model.layers.5.mlp.gate_proj.biases": "model.safetensors",
|
| 636 |
-
"model.layers.5.mlp.gate_proj.scales": "model.safetensors",
|
| 637 |
-
"model.layers.5.mlp.gate_proj.weight": "model.safetensors",
|
| 638 |
-
"model.layers.5.mlp.up_proj.biases": "model.safetensors",
|
| 639 |
-
"model.layers.5.mlp.up_proj.scales": "model.safetensors",
|
| 640 |
-
"model.layers.5.mlp.up_proj.weight": "model.safetensors",
|
| 641 |
-
"model.layers.5.post_attention_layernorm.weight": "model.safetensors",
|
| 642 |
-
"model.layers.5.self_attn.k_proj.biases": "model.safetensors",
|
| 643 |
-
"model.layers.5.self_attn.k_proj.scales": "model.safetensors",
|
| 644 |
-
"model.layers.5.self_attn.k_proj.weight": "model.safetensors",
|
| 645 |
-
"model.layers.5.self_attn.o_proj.biases": "model.safetensors",
|
| 646 |
-
"model.layers.5.self_attn.o_proj.scales": "model.safetensors",
|
| 647 |
-
"model.layers.5.self_attn.o_proj.weight": "model.safetensors",
|
| 648 |
-
"model.layers.5.self_attn.q_proj.biases": "model.safetensors",
|
| 649 |
-
"model.layers.5.self_attn.q_proj.scales": "model.safetensors",
|
| 650 |
-
"model.layers.5.self_attn.q_proj.weight": "model.safetensors",
|
| 651 |
-
"model.layers.5.self_attn.v_proj.biases": "model.safetensors",
|
| 652 |
-
"model.layers.5.self_attn.v_proj.scales": "model.safetensors",
|
| 653 |
-
"model.layers.5.self_attn.v_proj.weight": "model.safetensors",
|
| 654 |
-
"model.layers.6.input_layernorm.weight": "model.safetensors",
|
| 655 |
-
"model.layers.6.mlp.down_proj.biases": "model.safetensors",
|
| 656 |
-
"model.layers.6.mlp.down_proj.scales": "model.safetensors",
|
| 657 |
-
"model.layers.6.mlp.down_proj.weight": "model.safetensors",
|
| 658 |
-
"model.layers.6.mlp.gate_proj.biases": "model.safetensors",
|
| 659 |
-
"model.layers.6.mlp.gate_proj.scales": "model.safetensors",
|
| 660 |
-
"model.layers.6.mlp.gate_proj.weight": "model.safetensors",
|
| 661 |
-
"model.layers.6.mlp.up_proj.biases": "model.safetensors",
|
| 662 |
-
"model.layers.6.mlp.up_proj.scales": "model.safetensors",
|
| 663 |
-
"model.layers.6.mlp.up_proj.weight": "model.safetensors",
|
| 664 |
-
"model.layers.6.post_attention_layernorm.weight": "model.safetensors",
|
| 665 |
-
"model.layers.6.self_attn.k_proj.biases": "model.safetensors",
|
| 666 |
-
"model.layers.6.self_attn.k_proj.scales": "model.safetensors",
|
| 667 |
-
"model.layers.6.self_attn.k_proj.weight": "model.safetensors",
|
| 668 |
-
"model.layers.6.self_attn.o_proj.biases": "model.safetensors",
|
| 669 |
-
"model.layers.6.self_attn.o_proj.scales": "model.safetensors",
|
| 670 |
-
"model.layers.6.self_attn.o_proj.weight": "model.safetensors",
|
| 671 |
-
"model.layers.6.self_attn.q_proj.biases": "model.safetensors",
|
| 672 |
-
"model.layers.6.self_attn.q_proj.scales": "model.safetensors",
|
| 673 |
-
"model.layers.6.self_attn.q_proj.weight": "model.safetensors",
|
| 674 |
-
"model.layers.6.self_attn.v_proj.biases": "model.safetensors",
|
| 675 |
-
"model.layers.6.self_attn.v_proj.scales": "model.safetensors",
|
| 676 |
-
"model.layers.6.self_attn.v_proj.weight": "model.safetensors",
|
| 677 |
-
"model.layers.7.input_layernorm.weight": "model.safetensors",
|
| 678 |
-
"model.layers.7.mlp.down_proj.biases": "model.safetensors",
|
| 679 |
-
"model.layers.7.mlp.down_proj.scales": "model.safetensors",
|
| 680 |
-
"model.layers.7.mlp.down_proj.weight": "model.safetensors",
|
| 681 |
-
"model.layers.7.mlp.gate_proj.biases": "model.safetensors",
|
| 682 |
-
"model.layers.7.mlp.gate_proj.scales": "model.safetensors",
|
| 683 |
-
"model.layers.7.mlp.gate_proj.weight": "model.safetensors",
|
| 684 |
-
"model.layers.7.mlp.up_proj.biases": "model.safetensors",
|
| 685 |
-
"model.layers.7.mlp.up_proj.scales": "model.safetensors",
|
| 686 |
-
"model.layers.7.mlp.up_proj.weight": "model.safetensors",
|
| 687 |
-
"model.layers.7.post_attention_layernorm.weight": "model.safetensors",
|
| 688 |
-
"model.layers.7.self_attn.k_proj.biases": "model.safetensors",
|
| 689 |
-
"model.layers.7.self_attn.k_proj.scales": "model.safetensors",
|
| 690 |
-
"model.layers.7.self_attn.k_proj.weight": "model.safetensors",
|
| 691 |
-
"model.layers.7.self_attn.o_proj.biases": "model.safetensors",
|
| 692 |
-
"model.layers.7.self_attn.o_proj.scales": "model.safetensors",
|
| 693 |
-
"model.layers.7.self_attn.o_proj.weight": "model.safetensors",
|
| 694 |
-
"model.layers.7.self_attn.q_proj.biases": "model.safetensors",
|
| 695 |
-
"model.layers.7.self_attn.q_proj.scales": "model.safetensors",
|
| 696 |
-
"model.layers.7.self_attn.q_proj.weight": "model.safetensors",
|
| 697 |
-
"model.layers.7.self_attn.v_proj.biases": "model.safetensors",
|
| 698 |
-
"model.layers.7.self_attn.v_proj.scales": "model.safetensors",
|
| 699 |
-
"model.layers.7.self_attn.v_proj.weight": "model.safetensors",
|
| 700 |
-
"model.layers.8.input_layernorm.weight": "model.safetensors",
|
| 701 |
-
"model.layers.8.mlp.down_proj.biases": "model.safetensors",
|
| 702 |
-
"model.layers.8.mlp.down_proj.scales": "model.safetensors",
|
| 703 |
-
"model.layers.8.mlp.down_proj.weight": "model.safetensors",
|
| 704 |
-
"model.layers.8.mlp.gate_proj.biases": "model.safetensors",
|
| 705 |
-
"model.layers.8.mlp.gate_proj.scales": "model.safetensors",
|
| 706 |
-
"model.layers.8.mlp.gate_proj.weight": "model.safetensors",
|
| 707 |
-
"model.layers.8.mlp.up_proj.biases": "model.safetensors",
|
| 708 |
-
"model.layers.8.mlp.up_proj.scales": "model.safetensors",
|
| 709 |
-
"model.layers.8.mlp.up_proj.weight": "model.safetensors",
|
| 710 |
-
"model.layers.8.post_attention_layernorm.weight": "model.safetensors",
|
| 711 |
-
"model.layers.8.self_attn.k_proj.biases": "model.safetensors",
|
| 712 |
-
"model.layers.8.self_attn.k_proj.scales": "model.safetensors",
|
| 713 |
-
"model.layers.8.self_attn.k_proj.weight": "model.safetensors",
|
| 714 |
-
"model.layers.8.self_attn.o_proj.biases": "model.safetensors",
|
| 715 |
-
"model.layers.8.self_attn.o_proj.scales": "model.safetensors",
|
| 716 |
-
"model.layers.8.self_attn.o_proj.weight": "model.safetensors",
|
| 717 |
-
"model.layers.8.self_attn.q_proj.biases": "model.safetensors",
|
| 718 |
-
"model.layers.8.self_attn.q_proj.scales": "model.safetensors",
|
| 719 |
-
"model.layers.8.self_attn.q_proj.weight": "model.safetensors",
|
| 720 |
-
"model.layers.8.self_attn.v_proj.biases": "model.safetensors",
|
| 721 |
-
"model.layers.8.self_attn.v_proj.scales": "model.safetensors",
|
| 722 |
-
"model.layers.8.self_attn.v_proj.weight": "model.safetensors",
|
| 723 |
-
"model.layers.9.input_layernorm.weight": "model.safetensors",
|
| 724 |
-
"model.layers.9.mlp.down_proj.biases": "model.safetensors",
|
| 725 |
-
"model.layers.9.mlp.down_proj.scales": "model.safetensors",
|
| 726 |
-
"model.layers.9.mlp.down_proj.weight": "model.safetensors",
|
| 727 |
-
"model.layers.9.mlp.gate_proj.biases": "model.safetensors",
|
| 728 |
-
"model.layers.9.mlp.gate_proj.scales": "model.safetensors",
|
| 729 |
-
"model.layers.9.mlp.gate_proj.weight": "model.safetensors",
|
| 730 |
-
"model.layers.9.mlp.up_proj.biases": "model.safetensors",
|
| 731 |
-
"model.layers.9.mlp.up_proj.scales": "model.safetensors",
|
| 732 |
-
"model.layers.9.mlp.up_proj.weight": "model.safetensors",
|
| 733 |
-
"model.layers.9.post_attention_layernorm.weight": "model.safetensors",
|
| 734 |
-
"model.layers.9.self_attn.k_proj.biases": "model.safetensors",
|
| 735 |
-
"model.layers.9.self_attn.k_proj.scales": "model.safetensors",
|
| 736 |
-
"model.layers.9.self_attn.k_proj.weight": "model.safetensors",
|
| 737 |
-
"model.layers.9.self_attn.o_proj.biases": "model.safetensors",
|
| 738 |
-
"model.layers.9.self_attn.o_proj.scales": "model.safetensors",
|
| 739 |
-
"model.layers.9.self_attn.o_proj.weight": "model.safetensors",
|
| 740 |
-
"model.layers.9.self_attn.q_proj.biases": "model.safetensors",
|
| 741 |
-
"model.layers.9.self_attn.q_proj.scales": "model.safetensors",
|
| 742 |
-
"model.layers.9.self_attn.q_proj.weight": "model.safetensors",
|
| 743 |
-
"model.layers.9.self_attn.v_proj.biases": "model.safetensors",
|
| 744 |
-
"model.layers.9.self_attn.v_proj.scales": "model.safetensors",
|
| 745 |
-
"model.layers.9.self_attn.v_proj.weight": "model.safetensors",
|
| 746 |
-
"model.norm.weight": "model.safetensors"
|
| 747 |
}
|
| 748 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 14483464192
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00002-of-00003.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00003-of-00003.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 296 |
+
"model.norm.weight": "model-00002-of-00003.safetensors"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 297 |
}
|
| 298 |
}
|
tokenizer.json
CHANGED
|
@@ -31,23 +31,13 @@
|
|
| 31 |
"special": true
|
| 32 |
}
|
| 33 |
],
|
| 34 |
-
"normalizer":
|
| 35 |
-
|
| 36 |
-
"
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
},
|
| 41 |
-
{
|
| 42 |
-
"type": "Replace",
|
| 43 |
-
"pattern": {
|
| 44 |
-
"String": " "
|
| 45 |
-
},
|
| 46 |
-
"content": "▁"
|
| 47 |
-
}
|
| 48 |
-
]
|
| 49 |
},
|
| 50 |
-
"pre_tokenizer": null,
|
| 51 |
"post_processor": {
|
| 52 |
"type": "TemplateProcessing",
|
| 53 |
"single": [
|
|
@@ -134,6 +124,7 @@
|
|
| 134 |
"end_of_word_suffix": null,
|
| 135 |
"fuse_unk": true,
|
| 136 |
"byte_fallback": true,
|
|
|
|
| 137 |
"vocab": {
|
| 138 |
"<unk>": 0,
|
| 139 |
"<s>": 1,
|
|
|
|
| 31 |
"special": true
|
| 32 |
}
|
| 33 |
],
|
| 34 |
+
"normalizer": null,
|
| 35 |
+
"pre_tokenizer": {
|
| 36 |
+
"type": "Metaspace",
|
| 37 |
+
"replacement": "▁",
|
| 38 |
+
"prepend_scheme": "first",
|
| 39 |
+
"split": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
},
|
|
|
|
| 41 |
"post_processor": {
|
| 42 |
"type": "TemplateProcessing",
|
| 43 |
"single": [
|
|
|
|
| 124 |
"end_of_word_suffix": null,
|
| 125 |
"fuse_unk": true,
|
| 126 |
"byte_fallback": true,
|
| 127 |
+
"ignore_merges": false,
|
| 128 |
"vocab": {
|
| 129 |
"<unk>": 0,
|
| 130 |
"<s>": 1,
|
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
|
|
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
@@ -29,10 +30,10 @@
|
|
| 29 |
},
|
| 30 |
"additional_special_tokens": [],
|
| 31 |
"bos_token": "<s>",
|
| 32 |
-
"chat_template": "{{
|
| 33 |
"clean_up_tokenization_spaces": false,
|
| 34 |
"eos_token": "</s>",
|
| 35 |
-
"legacy":
|
| 36 |
"model_max_length": 1000000000000000019884624838656,
|
| 37 |
"pad_token": null,
|
| 38 |
"sp_model_kwargs": {},
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": true,
|
| 3 |
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
"content": "<unk>",
|
|
|
|
| 30 |
},
|
| 31 |
"additional_special_tokens": [],
|
| 32 |
"bos_token": "<s>",
|
| 33 |
+
"chat_template": "{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message['role'] == 'user' %}\n {%- if loop.first and system_message is defined %}\n {{- ' [INST] ' + system_message + '\\n\\n' + message['content'] + ' [/INST]' }}\n {%- else %}\n {{- ' [INST] ' + message['content'] + ' [/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {{- ' ' + message['content'] + eos_token}}\n {%- else %}\n {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n {%- endif %}\n{%- endfor %}\n",
|
| 34 |
"clean_up_tokenization_spaces": false,
|
| 35 |
"eos_token": "</s>",
|
| 36 |
+
"legacy": false,
|
| 37 |
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
"pad_token": null,
|
| 39 |
"sp_model_kwargs": {},
|