Upload folder using huggingface_hub
Browse files- config.json +9 -10
- eval_dev_token_acc.json +8 -0
- latest +1 -1
- long2short_proportions.json +130 -196
- model-00001-of-00006.safetensors +3 -0
- model-00002-of-00006.safetensors +3 -0
- model-00003-of-00006.safetensors +3 -0
- model-00004-of-00006.safetensors +3 -0
- model-00005-of-00006.safetensors +3 -0
- model-00006-of-00006.safetensors +3 -0
- model.safetensors.index.json +580 -340
- rng_state_0.pth +2 -2
- rng_state_1.pth +2 -2
- rng_state_2.pth +2 -2
- rng_state_3.pth +2 -2
- rng_state_4.pth +2 -2
- rng_state_5.pth +2 -2
- rng_state_6.pth +2 -2
- rng_state_7.pth +2 -2
- scheduler.pt +1 -1
- tokenizer_config.json +1 -1
- trainer_state.json +0 -0
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/cpfs/user/lizhongzhi/huggingface_model/huggingface_model/DeepSeek-R1-Distill-Qwen-
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
|
@@ -7,25 +7,24 @@
|
|
| 7 |
"bos_token_id": 151643,
|
| 8 |
"eos_token_id": 151643,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
-
"hidden_size":
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
-
"intermediate_size":
|
| 13 |
"max_position_embeddings": 131072,
|
| 14 |
-
"max_window_layers":
|
| 15 |
"model_type": "qwen2",
|
| 16 |
-
"num_attention_heads":
|
| 17 |
-
"num_hidden_layers":
|
| 18 |
-
"num_key_value_heads":
|
| 19 |
"pad_token_id": 151643,
|
| 20 |
-
"rms_norm_eps": 1e-
|
| 21 |
"rope_scaling": null,
|
| 22 |
-
"rope_theta":
|
| 23 |
"sliding_window": null,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
"transformers_version": "4.46.3",
|
| 27 |
"use_cache": true,
|
| 28 |
-
"use_mrope": false,
|
| 29 |
"use_sliding_window": false,
|
| 30 |
"vocab_size": 152064
|
| 31 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/cpfs/user/lizhongzhi/huggingface_model/huggingface_model/DeepSeek-R1-Distill-Qwen-14B/",
|
| 3 |
"architectures": [
|
| 4 |
"Qwen2ForCausalLM"
|
| 5 |
],
|
|
|
|
| 7 |
"bos_token_id": 151643,
|
| 8 |
"eos_token_id": 151643,
|
| 9 |
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 5120,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 13824,
|
| 13 |
"max_position_embeddings": 131072,
|
| 14 |
+
"max_window_layers": 48,
|
| 15 |
"model_type": "qwen2",
|
| 16 |
+
"num_attention_heads": 40,
|
| 17 |
+
"num_hidden_layers": 48,
|
| 18 |
+
"num_key_value_heads": 8,
|
| 19 |
"pad_token_id": 151643,
|
| 20 |
+
"rms_norm_eps": 1e-05,
|
| 21 |
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000.0,
|
| 23 |
"sliding_window": null,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
"torch_dtype": "bfloat16",
|
| 26 |
"transformers_version": "4.46.3",
|
| 27 |
"use_cache": true,
|
|
|
|
| 28 |
"use_sliding_window": false,
|
| 29 |
"vocab_size": 152064
|
| 30 |
}
|
eval_dev_token_acc.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eval_dev_token": 4446.53125,
|
| 3 |
+
"eval_dev_acc": 0.513671875,
|
| 4 |
+
"eval_runtime": 329.208,
|
| 5 |
+
"eval_samples_per_second": 0.194,
|
| 6 |
+
"eval_steps_per_second": 0.003,
|
| 7 |
+
"epoch": 0.416
|
| 8 |
+
}
|
latest
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
global_step832
|
long2short_proportions.json
CHANGED
|
@@ -6,360 +6,294 @@
|
|
| 6 |
0.2
|
| 7 |
],
|
| 8 |
"cot_domain_name": [
|
| 9 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 10 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 11 |
-
]
|
| 12 |
-
},
|
| 13 |
-
{
|
| 14 |
-
"global_step": 8,
|
| 15 |
-
"cot_domain_weight": [
|
| 16 |
-
0.81966233253479,
|
| 17 |
-
0.18033766746520996
|
| 18 |
-
],
|
| 19 |
-
"cot_domain_name": [
|
| 20 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/long2short_prm12k_gsm8k_merge_data/dynamic_long_short_data/gsm8k_prm12k_s1/prm12k_gsm8k_short_shortest.jsonl",
|
| 21 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/liang/s1_7b_r1_prompt.jsonl"
|
| 22 |
-
]
|
| 23 |
-
},
|
| 24 |
-
{
|
| 25 |
-
"global_step": 16,
|
| 26 |
-
"cot_domain_weight": [
|
| 27 |
-
0.7872583270072937,
|
| 28 |
-
0.2127416729927063
|
| 29 |
-
],
|
| 30 |
-
"cot_domain_name": [
|
| 31 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/long2short_prm12k_gsm8k_merge_data/dynamic_long_short_data/gsm8k_prm12k_s1/prm12k_gsm8k_short_shortest.jsonl",
|
| 32 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/liang/s1_7b_r1_prompt.jsonl"
|
| 33 |
-
]
|
| 34 |
-
},
|
| 35 |
-
{
|
| 36 |
-
"global_step": 24,
|
| 37 |
-
"cot_domain_weight": [
|
| 38 |
-
0.7460198998451233,
|
| 39 |
-
0.2539801001548767
|
| 40 |
-
],
|
| 41 |
-
"cot_domain_name": [
|
| 42 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/long2short_prm12k_gsm8k_merge_data/dynamic_long_short_data/gsm8k_prm12k_s1/prm12k_gsm8k_short_shortest.jsonl",
|
| 43 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/liang/s1_7b_r1_prompt.jsonl"
|
| 44 |
]
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"global_step": 32,
|
| 48 |
"cot_domain_weight": [
|
| 49 |
-
0.
|
| 50 |
-
0.
|
| 51 |
-
],
|
| 52 |
-
"cot_domain_name": [
|
| 53 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/long2short_prm12k_gsm8k_merge_data/dynamic_long_short_data/gsm8k_prm12k_s1/prm12k_gsm8k_short_shortest.jsonl",
|
| 54 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/liang/s1_7b_r1_prompt.jsonl"
|
| 55 |
-
]
|
| 56 |
-
},
|
| 57 |
-
{
|
| 58 |
-
"global_step": 40,
|
| 59 |
-
"cot_domain_weight": [
|
| 60 |
-
0.5970645546913147,
|
| 61 |
-
0.4029354453086853
|
| 62 |
],
|
| 63 |
"cot_domain_name": [
|
| 64 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 65 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 66 |
-
]
|
| 67 |
-
},
|
| 68 |
-
{
|
| 69 |
-
"global_step": 48,
|
| 70 |
-
"cot_domain_weight": [
|
| 71 |
-
0.3999738454834315,
|
| 72 |
-
0.6000261545165685
|
| 73 |
-
],
|
| 74 |
-
"cot_domain_name": [
|
| 75 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/long2short_prm12k_gsm8k_merge_data/dynamic_long_short_data/gsm8k_prm12k_s1/prm12k_gsm8k_short_shortest.jsonl",
|
| 76 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/liang/s1_7b_r1_prompt.jsonl"
|
| 77 |
-
]
|
| 78 |
-
},
|
| 79 |
-
{
|
| 80 |
-
"global_step": 56,
|
| 81 |
-
"cot_domain_weight": [
|
| 82 |
-
0.2720071835522165,
|
| 83 |
-
0.7279928164477835
|
| 84 |
-
],
|
| 85 |
-
"cot_domain_name": [
|
| 86 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/long2short_prm12k_gsm8k_merge_data/dynamic_long_short_data/gsm8k_prm12k_s1/prm12k_gsm8k_short_shortest.jsonl",
|
| 87 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/liang/s1_7b_r1_prompt.jsonl"
|
| 88 |
]
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"global_step": 64,
|
| 92 |
"cot_domain_weight": [
|
| 93 |
-
0.
|
| 94 |
-
0.
|
| 95 |
],
|
| 96 |
"cot_domain_name": [
|
| 97 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 98 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 99 |
]
|
| 100 |
},
|
| 101 |
{
|
| 102 |
-
"global_step":
|
| 103 |
"cot_domain_weight": [
|
| 104 |
-
0.
|
| 105 |
-
0.
|
| 106 |
],
|
| 107 |
"cot_domain_name": [
|
| 108 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 109 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 110 |
]
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"global_step":
|
| 114 |
"cot_domain_weight": [
|
| 115 |
-
0.
|
| 116 |
-
0.
|
| 117 |
],
|
| 118 |
"cot_domain_name": [
|
| 119 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 120 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 121 |
]
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"global_step":
|
| 125 |
"cot_domain_weight": [
|
| 126 |
-
0.
|
| 127 |
-
0.
|
| 128 |
],
|
| 129 |
"cot_domain_name": [
|
| 130 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 131 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 132 |
]
|
| 133 |
},
|
| 134 |
{
|
| 135 |
-
"global_step":
|
| 136 |
"cot_domain_weight": [
|
| 137 |
-
0.
|
| 138 |
-
0.
|
| 139 |
],
|
| 140 |
"cot_domain_name": [
|
| 141 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 142 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 143 |
]
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"global_step":
|
| 147 |
"cot_domain_weight": [
|
| 148 |
-
0.
|
| 149 |
-
0.
|
| 150 |
],
|
| 151 |
"cot_domain_name": [
|
| 152 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 153 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 154 |
]
|
| 155 |
},
|
| 156 |
{
|
| 157 |
-
"global_step":
|
| 158 |
"cot_domain_weight": [
|
| 159 |
-
0.
|
| 160 |
-
0.
|
| 161 |
],
|
| 162 |
"cot_domain_name": [
|
| 163 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 164 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 165 |
]
|
| 166 |
},
|
| 167 |
{
|
| 168 |
-
"global_step":
|
| 169 |
"cot_domain_weight": [
|
| 170 |
-
0.
|
| 171 |
-
0.
|
| 172 |
],
|
| 173 |
"cot_domain_name": [
|
| 174 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 175 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 176 |
]
|
| 177 |
},
|
| 178 |
{
|
| 179 |
-
"global_step":
|
| 180 |
"cot_domain_weight": [
|
| 181 |
-
0.
|
| 182 |
-
0.
|
| 183 |
],
|
| 184 |
"cot_domain_name": [
|
| 185 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 186 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 187 |
]
|
| 188 |
},
|
| 189 |
{
|
| 190 |
-
"global_step":
|
| 191 |
"cot_domain_weight": [
|
| 192 |
-
0.
|
| 193 |
-
0.
|
| 194 |
],
|
| 195 |
"cot_domain_name": [
|
| 196 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 197 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 198 |
]
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"global_step":
|
| 202 |
"cot_domain_weight": [
|
| 203 |
-
0.
|
| 204 |
-
0.
|
| 205 |
],
|
| 206 |
"cot_domain_name": [
|
| 207 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 208 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 209 |
]
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"global_step":
|
| 213 |
"cot_domain_weight": [
|
| 214 |
-
0.
|
| 215 |
-
0.
|
| 216 |
],
|
| 217 |
"cot_domain_name": [
|
| 218 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 219 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 220 |
]
|
| 221 |
},
|
| 222 |
{
|
| 223 |
-
"global_step":
|
| 224 |
"cot_domain_weight": [
|
| 225 |
-
0.
|
| 226 |
-
0.
|
| 227 |
],
|
| 228 |
"cot_domain_name": [
|
| 229 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 230 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 231 |
]
|
| 232 |
},
|
| 233 |
{
|
| 234 |
-
"global_step":
|
| 235 |
"cot_domain_weight": [
|
| 236 |
-
0.
|
| 237 |
-
0.
|
| 238 |
],
|
| 239 |
"cot_domain_name": [
|
| 240 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 241 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 242 |
]
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"global_step":
|
| 246 |
"cot_domain_weight": [
|
| 247 |
-
0.
|
| 248 |
-
0.
|
| 249 |
],
|
| 250 |
"cot_domain_name": [
|
| 251 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 252 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 253 |
]
|
| 254 |
},
|
| 255 |
{
|
| 256 |
-
"global_step":
|
| 257 |
"cot_domain_weight": [
|
| 258 |
-
0.
|
| 259 |
-
0.
|
| 260 |
],
|
| 261 |
"cot_domain_name": [
|
| 262 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 263 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 264 |
]
|
| 265 |
},
|
| 266 |
{
|
| 267 |
-
"global_step":
|
| 268 |
"cot_domain_weight": [
|
| 269 |
-
0.
|
| 270 |
-
0.
|
| 271 |
],
|
| 272 |
"cot_domain_name": [
|
| 273 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 274 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 275 |
]
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"global_step":
|
| 279 |
"cot_domain_weight": [
|
| 280 |
-
0.
|
| 281 |
-
0.
|
| 282 |
],
|
| 283 |
"cot_domain_name": [
|
| 284 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 285 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 286 |
]
|
| 287 |
},
|
| 288 |
{
|
| 289 |
-
"global_step":
|
| 290 |
"cot_domain_weight": [
|
| 291 |
-
0.
|
| 292 |
-
0.
|
| 293 |
],
|
| 294 |
"cot_domain_name": [
|
| 295 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 296 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 297 |
]
|
| 298 |
},
|
| 299 |
{
|
| 300 |
-
"global_step":
|
| 301 |
"cot_domain_weight": [
|
| 302 |
-
0.
|
| 303 |
-
0.
|
| 304 |
],
|
| 305 |
"cot_domain_name": [
|
| 306 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 307 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 308 |
]
|
| 309 |
},
|
| 310 |
{
|
| 311 |
-
"global_step":
|
| 312 |
"cot_domain_weight": [
|
| 313 |
-
0.
|
| 314 |
-
0.
|
| 315 |
],
|
| 316 |
"cot_domain_name": [
|
| 317 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 318 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 319 |
]
|
| 320 |
},
|
| 321 |
{
|
| 322 |
-
"global_step":
|
| 323 |
"cot_domain_weight": [
|
| 324 |
-
0.
|
| 325 |
-
0.
|
| 326 |
],
|
| 327 |
"cot_domain_name": [
|
| 328 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 329 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 330 |
]
|
| 331 |
},
|
| 332 |
{
|
| 333 |
-
"global_step":
|
| 334 |
"cot_domain_weight": [
|
| 335 |
-
0.
|
| 336 |
-
0.
|
| 337 |
],
|
| 338 |
"cot_domain_name": [
|
| 339 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 340 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 341 |
]
|
| 342 |
},
|
| 343 |
{
|
| 344 |
-
"global_step":
|
| 345 |
"cot_domain_weight": [
|
| 346 |
-
0.
|
| 347 |
-
0.
|
| 348 |
],
|
| 349 |
"cot_domain_name": [
|
| 350 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 351 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 352 |
]
|
| 353 |
},
|
| 354 |
{
|
| 355 |
-
"global_step":
|
| 356 |
"cot_domain_weight": [
|
| 357 |
-
0.
|
| 358 |
-
0.
|
| 359 |
],
|
| 360 |
"cot_domain_name": [
|
| 361 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 362 |
-
"/cpfs/user/lizhongzhi/data/data/gsm8k/
|
| 363 |
]
|
| 364 |
}
|
| 365 |
]
|
|
|
|
| 6 |
0.2
|
| 7 |
],
|
| 8 |
"cot_domain_name": [
|
| 9 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 10 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
]
|
| 12 |
},
|
| 13 |
{
|
| 14 |
"global_step": 32,
|
| 15 |
"cot_domain_weight": [
|
| 16 |
+
0.8388444060259401,
|
| 17 |
+
0.1611555939740599
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
],
|
| 19 |
"cot_domain_name": [
|
| 20 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 21 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
]
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"global_step": 64,
|
| 26 |
"cot_domain_weight": [
|
| 27 |
+
0.8505354307831271,
|
| 28 |
+
0.14946456921687287
|
| 29 |
],
|
| 30 |
"cot_domain_name": [
|
| 31 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 32 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 33 |
]
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"global_step": 96,
|
| 37 |
"cot_domain_weight": [
|
| 38 |
+
0.924430987039901,
|
| 39 |
+
0.07556901296009898
|
| 40 |
],
|
| 41 |
"cot_domain_name": [
|
| 42 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 43 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 44 |
]
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"global_step": 128,
|
| 48 |
"cot_domain_weight": [
|
| 49 |
+
0.9291076840859197,
|
| 50 |
+
0.07089231591408032
|
| 51 |
],
|
| 52 |
"cot_domain_name": [
|
| 53 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 54 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 55 |
]
|
| 56 |
},
|
| 57 |
{
|
| 58 |
+
"global_step": 160,
|
| 59 |
"cot_domain_weight": [
|
| 60 |
+
0.9551703627379949,
|
| 61 |
+
0.044829637262005104
|
| 62 |
],
|
| 63 |
"cot_domain_name": [
|
| 64 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 65 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 66 |
]
|
| 67 |
},
|
| 68 |
{
|
| 69 |
+
"global_step": 192,
|
| 70 |
"cot_domain_weight": [
|
| 71 |
+
0.9511838867907558,
|
| 72 |
+
0.048816113209244213
|
| 73 |
],
|
| 74 |
"cot_domain_name": [
|
| 75 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 76 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 77 |
]
|
| 78 |
},
|
| 79 |
{
|
| 80 |
+
"global_step": 224,
|
| 81 |
"cot_domain_weight": [
|
| 82 |
+
0.959743360270474,
|
| 83 |
+
0.040256639729526034
|
| 84 |
],
|
| 85 |
"cot_domain_name": [
|
| 86 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 87 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 88 |
]
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"global_step": 256,
|
| 92 |
"cot_domain_weight": [
|
| 93 |
+
0.9756809723788156,
|
| 94 |
+
0.02431902762118443
|
| 95 |
],
|
| 96 |
"cot_domain_name": [
|
| 97 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 98 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 99 |
]
|
| 100 |
},
|
| 101 |
{
|
| 102 |
+
"global_step": 288,
|
| 103 |
"cot_domain_weight": [
|
| 104 |
+
0.9798199552666768,
|
| 105 |
+
0.02018004473332324
|
| 106 |
],
|
| 107 |
"cot_domain_name": [
|
| 108 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 109 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 110 |
]
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"global_step": 320,
|
| 114 |
"cot_domain_weight": [
|
| 115 |
+
0.9872426298703754,
|
| 116 |
+
0.01275737012962466
|
| 117 |
],
|
| 118 |
"cot_domain_name": [
|
| 119 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 120 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 121 |
]
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"global_step": 352,
|
| 125 |
"cot_domain_weight": [
|
| 126 |
+
0.9888833217843287,
|
| 127 |
+
0.011116678215671317
|
| 128 |
],
|
| 129 |
"cot_domain_name": [
|
| 130 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 131 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 132 |
]
|
| 133 |
},
|
| 134 |
{
|
| 135 |
+
"global_step": 384,
|
| 136 |
"cot_domain_weight": [
|
| 137 |
+
0.9933160784608732,
|
| 138 |
+
0.006683921539126801
|
| 139 |
],
|
| 140 |
"cot_domain_name": [
|
| 141 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 142 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 143 |
]
|
| 144 |
},
|
| 145 |
{
|
| 146 |
+
"global_step": 416,
|
| 147 |
"cot_domain_weight": [
|
| 148 |
+
0.9891085129978076,
|
| 149 |
+
0.010891487002192397
|
| 150 |
],
|
| 151 |
"cot_domain_name": [
|
| 152 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 153 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 154 |
]
|
| 155 |
},
|
| 156 |
{
|
| 157 |
+
"global_step": 448,
|
| 158 |
"cot_domain_weight": [
|
| 159 |
+
0.9930044565206148,
|
| 160 |
+
0.00699554347938529
|
| 161 |
],
|
| 162 |
"cot_domain_name": [
|
| 163 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 164 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 165 |
]
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"global_step": 480,
|
| 169 |
"cot_domain_weight": [
|
| 170 |
+
0.9946519011372694,
|
| 171 |
+
0.0053480988627305865
|
| 172 |
],
|
| 173 |
"cot_domain_name": [
|
| 174 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 175 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 176 |
]
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"global_step": 512,
|
| 180 |
"cot_domain_weight": [
|
| 181 |
+
0.9958559065994267,
|
| 182 |
+
0.0041440934005732635
|
| 183 |
],
|
| 184 |
"cot_domain_name": [
|
| 185 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 186 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 187 |
]
|
| 188 |
},
|
| 189 |
{
|
| 190 |
+
"global_step": 544,
|
| 191 |
"cot_domain_weight": [
|
| 192 |
+
0.9975449034946824,
|
| 193 |
+
0.0024550965053175616
|
| 194 |
],
|
| 195 |
"cot_domain_name": [
|
| 196 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 197 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 198 |
]
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"global_step": 576,
|
| 202 |
"cot_domain_weight": [
|
| 203 |
+
0.9979881855698594,
|
| 204 |
+
0.0020118144301406837
|
| 205 |
],
|
| 206 |
"cot_domain_name": [
|
| 207 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 208 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 209 |
]
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"global_step": 608,
|
| 213 |
"cot_domain_weight": [
|
| 214 |
+
0.9987150533759055,
|
| 215 |
+
0.001284946624094461
|
| 216 |
],
|
| 217 |
"cot_domain_name": [
|
| 218 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 219 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 220 |
]
|
| 221 |
},
|
| 222 |
{
|
| 223 |
+
"global_step": 640,
|
| 224 |
"cot_domain_weight": [
|
| 225 |
+
0.9985050461672554,
|
| 226 |
+
0.001494953832744527
|
| 227 |
],
|
| 228 |
"cot_domain_name": [
|
| 229 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 230 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 231 |
]
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"global_step": 672,
|
| 235 |
"cot_domain_weight": [
|
| 236 |
+
0.9985948003041136,
|
| 237 |
+
0.0014051996958864268
|
| 238 |
],
|
| 239 |
"cot_domain_name": [
|
| 240 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 241 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 242 |
]
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"global_step": 704,
|
| 246 |
"cot_domain_weight": [
|
| 247 |
+
0.9986131625707226,
|
| 248 |
+
0.0013868374292773191
|
| 249 |
],
|
| 250 |
"cot_domain_name": [
|
| 251 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 252 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 253 |
]
|
| 254 |
},
|
| 255 |
{
|
| 256 |
+
"global_step": 736,
|
| 257 |
"cot_domain_weight": [
|
| 258 |
+
0.9988695513983467,
|
| 259 |
+
0.0011304486016533988
|
| 260 |
],
|
| 261 |
"cot_domain_name": [
|
| 262 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 263 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 264 |
]
|
| 265 |
},
|
| 266 |
{
|
| 267 |
+
"global_step": 768,
|
| 268 |
"cot_domain_weight": [
|
| 269 |
+
0.9985235512457586,
|
| 270 |
+
0.0014764487542413534
|
| 271 |
],
|
| 272 |
"cot_domain_name": [
|
| 273 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 274 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 275 |
]
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"global_step": 800,
|
| 279 |
"cot_domain_weight": [
|
| 280 |
+
0.9983893508322773,
|
| 281 |
+
0.0016106491677227333
|
| 282 |
],
|
| 283 |
"cot_domain_name": [
|
| 284 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 285 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 286 |
]
|
| 287 |
},
|
| 288 |
{
|
| 289 |
+
"global_step": 832,
|
| 290 |
"cot_domain_weight": [
|
| 291 |
+
0.9938949698284351,
|
| 292 |
+
0.006105030171564917
|
| 293 |
],
|
| 294 |
"cot_domain_name": [
|
| 295 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/gsm8k_shortcot_outputs_ds_medium_length.jsonl",
|
| 296 |
+
"/cpfs/user/lizhongzhi/data/data/gsm8k/14b_data/s1_14b_longcot_outputs_ds.jsonl"
|
| 297 |
]
|
| 298 |
}
|
| 299 |
]
|
model-00001-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e28af04b1a542da0380afa4e4464d9205f9ac2e7a19d0b03eb45ae5bcb00a659
|
| 3 |
+
size 4986211280
|
model-00002-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d6702f09d6287482ba236921497c67f690f04aab565c45b761c8341d87b7400
|
| 3 |
+
size 4954847344
|
model-00003-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab8b5cd3fee9a3ac4db4e91097f51b9963f2644c6dd9004fe51bb6b7480654b7
|
| 3 |
+
size 4954847392
|
model-00004-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c5dce47229f535aaad68658c1fb1cbdc1de89c4027ddad03c8f744eb235a7b7
|
| 3 |
+
size 4954847392
|
model-00005-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68355f8ad433ecdcbd255a71e698c0b1d6f7518a3290fdaf050d7ccd6bcf1711
|
| 3 |
+
size 4954847392
|
model-00006-of-00006.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8552205d575c3ff6ee6b7ff90f99f5390a65e4cde121a6362c48fde04b17038e
|
| 3 |
+
size 4734533160
|
model.safetensors.index.json
CHANGED
|
@@ -1,346 +1,586 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
-
"lm_head.weight": "model-
|
| 7 |
-
"model.embed_tokens.weight": "model-00001-of-
|
| 8 |
-
"model.layers.0.input_layernorm.weight": "model-00001-of-
|
| 9 |
-
"model.layers.0.mlp.down_proj.weight": "model-00001-of-
|
| 10 |
-
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-
|
| 11 |
-
"model.layers.0.mlp.up_proj.weight": "model-00001-of-
|
| 12 |
-
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-
|
| 13 |
-
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-
|
| 14 |
-
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-
|
| 15 |
-
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-
|
| 16 |
-
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-
|
| 17 |
-
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-
|
| 18 |
-
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-
|
| 19 |
-
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-
|
| 20 |
-
"model.layers.1.input_layernorm.weight": "model-00001-of-
|
| 21 |
-
"model.layers.1.mlp.down_proj.weight": "model-00001-of-
|
| 22 |
-
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-
|
| 23 |
-
"model.layers.1.mlp.up_proj.weight": "model-00001-of-
|
| 24 |
-
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-
|
| 25 |
-
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-
|
| 26 |
-
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-
|
| 27 |
-
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-
|
| 28 |
-
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-
|
| 29 |
-
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-
|
| 30 |
-
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-
|
| 31 |
-
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-
|
| 32 |
-
"model.layers.10.input_layernorm.weight": "model-00002-of-
|
| 33 |
-
"model.layers.10.mlp.down_proj.weight": "model-00002-of-
|
| 34 |
-
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-
|
| 35 |
-
"model.layers.10.mlp.up_proj.weight": "model-00002-of-
|
| 36 |
-
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-
|
| 37 |
-
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-
|
| 38 |
-
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-
|
| 39 |
-
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-
|
| 40 |
-
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-
|
| 41 |
-
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-
|
| 42 |
-
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-
|
| 43 |
-
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-
|
| 44 |
-
"model.layers.11.input_layernorm.weight": "model-00002-of-
|
| 45 |
-
"model.layers.11.mlp.down_proj.weight": "model-00002-of-
|
| 46 |
-
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-
|
| 47 |
-
"model.layers.11.mlp.up_proj.weight": "model-00002-of-
|
| 48 |
-
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-
|
| 49 |
-
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-
|
| 50 |
-
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-
|
| 51 |
-
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-
|
| 52 |
-
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-
|
| 53 |
-
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-
|
| 54 |
-
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-
|
| 55 |
-
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-
|
| 56 |
-
"model.layers.12.input_layernorm.weight": "model-00002-of-
|
| 57 |
-
"model.layers.12.mlp.down_proj.weight": "model-00002-of-
|
| 58 |
-
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-
|
| 59 |
-
"model.layers.12.mlp.up_proj.weight": "model-00002-of-
|
| 60 |
-
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-
|
| 61 |
-
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-
|
| 62 |
-
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-
|
| 63 |
-
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-
|
| 64 |
-
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-
|
| 65 |
-
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-
|
| 66 |
-
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-
|
| 67 |
-
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-
|
| 68 |
-
"model.layers.13.input_layernorm.weight": "model-00002-of-
|
| 69 |
-
"model.layers.13.mlp.down_proj.weight": "model-00002-of-
|
| 70 |
-
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-
|
| 71 |
-
"model.layers.13.mlp.up_proj.weight": "model-00002-of-
|
| 72 |
-
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-
|
| 73 |
-
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-
|
| 74 |
-
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-
|
| 75 |
-
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-
|
| 76 |
-
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-
|
| 77 |
-
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-
|
| 78 |
-
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-
|
| 79 |
-
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-
|
| 80 |
-
"model.layers.14.input_layernorm.weight": "model-00002-of-
|
| 81 |
-
"model.layers.14.mlp.down_proj.weight": "model-00002-of-
|
| 82 |
-
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-
|
| 83 |
-
"model.layers.14.mlp.up_proj.weight": "model-00002-of-
|
| 84 |
-
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-
|
| 85 |
-
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-
|
| 86 |
-
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-
|
| 87 |
-
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-
|
| 88 |
-
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-
|
| 89 |
-
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-
|
| 90 |
-
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-
|
| 91 |
-
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-
|
| 92 |
-
"model.layers.15.input_layernorm.weight": "model-
|
| 93 |
-
"model.layers.15.mlp.down_proj.weight": "model-
|
| 94 |
-
"model.layers.15.mlp.gate_proj.weight": "model-
|
| 95 |
-
"model.layers.15.mlp.up_proj.weight": "model-
|
| 96 |
-
"model.layers.15.post_attention_layernorm.weight": "model-
|
| 97 |
-
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-
|
| 98 |
-
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-
|
| 99 |
-
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-
|
| 100 |
-
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-
|
| 101 |
-
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-
|
| 102 |
-
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-
|
| 103 |
-
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-
|
| 104 |
-
"model.layers.16.input_layernorm.weight": "model-
|
| 105 |
-
"model.layers.16.mlp.down_proj.weight": "model-
|
| 106 |
-
"model.layers.16.mlp.gate_proj.weight": "model-
|
| 107 |
-
"model.layers.16.mlp.up_proj.weight": "model-
|
| 108 |
-
"model.layers.16.post_attention_layernorm.weight": "model-
|
| 109 |
-
"model.layers.16.self_attn.k_proj.bias": "model-
|
| 110 |
-
"model.layers.16.self_attn.k_proj.weight": "model-
|
| 111 |
-
"model.layers.16.self_attn.o_proj.weight": "model-
|
| 112 |
-
"model.layers.16.self_attn.q_proj.bias": "model-
|
| 113 |
-
"model.layers.16.self_attn.q_proj.weight": "model-
|
| 114 |
-
"model.layers.16.self_attn.v_proj.bias": "model-
|
| 115 |
-
"model.layers.16.self_attn.v_proj.weight": "model-
|
| 116 |
-
"model.layers.17.input_layernorm.weight": "model-
|
| 117 |
-
"model.layers.17.mlp.down_proj.weight": "model-
|
| 118 |
-
"model.layers.17.mlp.gate_proj.weight": "model-
|
| 119 |
-
"model.layers.17.mlp.up_proj.weight": "model-
|
| 120 |
-
"model.layers.17.post_attention_layernorm.weight": "model-
|
| 121 |
-
"model.layers.17.self_attn.k_proj.bias": "model-
|
| 122 |
-
"model.layers.17.self_attn.k_proj.weight": "model-
|
| 123 |
-
"model.layers.17.self_attn.o_proj.weight": "model-
|
| 124 |
-
"model.layers.17.self_attn.q_proj.bias": "model-
|
| 125 |
-
"model.layers.17.self_attn.q_proj.weight": "model-
|
| 126 |
-
"model.layers.17.self_attn.v_proj.bias": "model-
|
| 127 |
-
"model.layers.17.self_attn.v_proj.weight": "model-
|
| 128 |
-
"model.layers.18.input_layernorm.weight": "model-00003-of-
|
| 129 |
-
"model.layers.18.mlp.down_proj.weight": "model-00003-of-
|
| 130 |
-
"model.layers.18.mlp.gate_proj.weight": "model-
|
| 131 |
-
"model.layers.18.mlp.up_proj.weight": "model-
|
| 132 |
-
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-
|
| 133 |
-
"model.layers.18.self_attn.k_proj.bias": "model-
|
| 134 |
-
"model.layers.18.self_attn.k_proj.weight": "model-
|
| 135 |
-
"model.layers.18.self_attn.o_proj.weight": "model-
|
| 136 |
-
"model.layers.18.self_attn.q_proj.bias": "model-
|
| 137 |
-
"model.layers.18.self_attn.q_proj.weight": "model-
|
| 138 |
-
"model.layers.18.self_attn.v_proj.bias": "model-
|
| 139 |
-
"model.layers.18.self_attn.v_proj.weight": "model-
|
| 140 |
-
"model.layers.19.input_layernorm.weight": "model-00003-of-
|
| 141 |
-
"model.layers.19.mlp.down_proj.weight": "model-00003-of-
|
| 142 |
-
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-
|
| 143 |
-
"model.layers.19.mlp.up_proj.weight": "model-00003-of-
|
| 144 |
-
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-
|
| 145 |
-
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-
|
| 146 |
-
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-
|
| 147 |
-
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-
|
| 148 |
-
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-
|
| 149 |
-
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-
|
| 150 |
-
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-
|
| 151 |
-
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-
|
| 152 |
-
"model.layers.2.input_layernorm.weight": "model-00001-of-
|
| 153 |
-
"model.layers.2.mlp.down_proj.weight": "model-00001-of-
|
| 154 |
-
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-
|
| 155 |
-
"model.layers.2.mlp.up_proj.weight": "model-00001-of-
|
| 156 |
-
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-
|
| 157 |
-
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-
|
| 158 |
-
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-
|
| 159 |
-
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-
|
| 160 |
-
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-
|
| 161 |
-
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-
|
| 162 |
-
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-
|
| 163 |
-
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-
|
| 164 |
-
"model.layers.20.input_layernorm.weight": "model-00003-of-
|
| 165 |
-
"model.layers.20.mlp.down_proj.weight": "model-00003-of-
|
| 166 |
-
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-
|
| 167 |
-
"model.layers.20.mlp.up_proj.weight": "model-00003-of-
|
| 168 |
-
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-
|
| 169 |
-
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-
|
| 170 |
-
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-
|
| 171 |
-
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-
|
| 172 |
-
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-
|
| 173 |
-
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-
|
| 174 |
-
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-
|
| 175 |
-
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-
|
| 176 |
-
"model.layers.21.input_layernorm.weight": "model-00003-of-
|
| 177 |
-
"model.layers.21.mlp.down_proj.weight": "model-00003-of-
|
| 178 |
-
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-
|
| 179 |
-
"model.layers.21.mlp.up_proj.weight": "model-00003-of-
|
| 180 |
-
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-
|
| 181 |
-
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-
|
| 182 |
-
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-
|
| 183 |
-
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-
|
| 184 |
-
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-
|
| 185 |
-
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-
|
| 186 |
-
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-
|
| 187 |
-
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-
|
| 188 |
-
"model.layers.22.input_layernorm.weight": "model-00003-of-
|
| 189 |
-
"model.layers.22.mlp.down_proj.weight": "model-00003-of-
|
| 190 |
-
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-
|
| 191 |
-
"model.layers.22.mlp.up_proj.weight": "model-00003-of-
|
| 192 |
-
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-
|
| 193 |
-
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-
|
| 194 |
-
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-
|
| 195 |
-
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-
|
| 196 |
-
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-
|
| 197 |
-
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-
|
| 198 |
-
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-
|
| 199 |
-
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-
|
| 200 |
-
"model.layers.23.input_layernorm.weight": "model-00003-of-
|
| 201 |
-
"model.layers.23.mlp.down_proj.weight": "model-00003-of-
|
| 202 |
-
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-
|
| 203 |
-
"model.layers.23.mlp.up_proj.weight": "model-00003-of-
|
| 204 |
-
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-
|
| 205 |
-
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-
|
| 206 |
-
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-
|
| 207 |
-
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-
|
| 208 |
-
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-
|
| 209 |
-
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-
|
| 210 |
-
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-
|
| 211 |
-
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-
|
| 212 |
-
"model.layers.24.input_layernorm.weight": "model-
|
| 213 |
-
"model.layers.24.mlp.down_proj.weight": "model-
|
| 214 |
-
"model.layers.24.mlp.gate_proj.weight": "model-
|
| 215 |
-
"model.layers.24.mlp.up_proj.weight": "model-
|
| 216 |
-
"model.layers.24.post_attention_layernorm.weight": "model-
|
| 217 |
-
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-
|
| 218 |
-
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-
|
| 219 |
-
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-
|
| 220 |
-
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-
|
| 221 |
-
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-
|
| 222 |
-
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-
|
| 223 |
-
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-
|
| 224 |
-
"model.layers.25.input_layernorm.weight": "model-
|
| 225 |
-
"model.layers.25.mlp.down_proj.weight": "model-
|
| 226 |
-
"model.layers.25.mlp.gate_proj.weight": "model-
|
| 227 |
-
"model.layers.25.mlp.up_proj.weight": "model-
|
| 228 |
-
"model.layers.25.post_attention_layernorm.weight": "model-
|
| 229 |
-
"model.layers.25.self_attn.k_proj.bias": "model-
|
| 230 |
-
"model.layers.25.self_attn.k_proj.weight": "model-
|
| 231 |
-
"model.layers.25.self_attn.o_proj.weight": "model-
|
| 232 |
-
"model.layers.25.self_attn.q_proj.bias": "model-
|
| 233 |
-
"model.layers.25.self_attn.q_proj.weight": "model-
|
| 234 |
-
"model.layers.25.self_attn.v_proj.bias": "model-
|
| 235 |
-
"model.layers.25.self_attn.v_proj.weight": "model-
|
| 236 |
-
"model.layers.26.input_layernorm.weight": "model-
|
| 237 |
-
"model.layers.26.mlp.down_proj.weight": "model-
|
| 238 |
-
"model.layers.26.mlp.gate_proj.weight": "model-
|
| 239 |
-
"model.layers.26.mlp.up_proj.weight": "model-
|
| 240 |
-
"model.layers.26.post_attention_layernorm.weight": "model-
|
| 241 |
-
"model.layers.26.self_attn.k_proj.bias": "model-
|
| 242 |
-
"model.layers.26.self_attn.k_proj.weight": "model-
|
| 243 |
-
"model.layers.26.self_attn.o_proj.weight": "model-
|
| 244 |
-
"model.layers.26.self_attn.q_proj.bias": "model-
|
| 245 |
-
"model.layers.26.self_attn.q_proj.weight": "model-
|
| 246 |
-
"model.layers.26.self_attn.v_proj.bias": "model-
|
| 247 |
-
"model.layers.26.self_attn.v_proj.weight": "model-
|
| 248 |
-
"model.layers.27.input_layernorm.weight": "model-
|
| 249 |
-
"model.layers.27.mlp.down_proj.weight": "model-
|
| 250 |
-
"model.layers.27.mlp.gate_proj.weight": "model-
|
| 251 |
-
"model.layers.27.mlp.up_proj.weight": "model-
|
| 252 |
-
"model.layers.27.post_attention_layernorm.weight": "model-
|
| 253 |
-
"model.layers.27.self_attn.k_proj.bias": "model-
|
| 254 |
-
"model.layers.27.self_attn.k_proj.weight": "model-
|
| 255 |
-
"model.layers.27.self_attn.o_proj.weight": "model-
|
| 256 |
-
"model.layers.27.self_attn.q_proj.bias": "model-
|
| 257 |
-
"model.layers.27.self_attn.q_proj.weight": "model-
|
| 258 |
-
"model.layers.27.self_attn.v_proj.bias": "model-
|
| 259 |
-
"model.layers.27.self_attn.v_proj.weight": "model-
|
| 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.layers.
|
| 297 |
-
"model.layers.
|
| 298 |
-
"model.layers.
|
| 299 |
-
"model.layers.
|
| 300 |
-
"model.layers.
|
| 301 |
-
"model.layers.
|
| 302 |
-
"model.layers.
|
| 303 |
-
"model.layers.
|
| 304 |
-
"model.layers.
|
| 305 |
-
"model.layers.
|
| 306 |
-
"model.layers.
|
| 307 |
-
"model.layers.
|
| 308 |
-
"model.layers.
|
| 309 |
-
"model.layers.
|
| 310 |
-
"model.layers.
|
| 311 |
-
"model.layers.
|
| 312 |
-
"model.layers.
|
| 313 |
-
"model.layers.
|
| 314 |
-
"model.layers.
|
| 315 |
-
"model.layers.
|
| 316 |
-
"model.layers.
|
| 317 |
-
"model.layers.
|
| 318 |
-
"model.layers.
|
| 319 |
-
"model.layers.
|
| 320 |
-
"model.layers.
|
| 321 |
-
"model.layers.
|
| 322 |
-
"model.layers.
|
| 323 |
-
"model.layers.
|
| 324 |
-
"model.layers.
|
| 325 |
-
"model.layers.
|
| 326 |
-
"model.layers.
|
| 327 |
-
"model.layers.
|
| 328 |
-
"model.layers.
|
| 329 |
-
"model.layers.
|
| 330 |
-
"model.layers.
|
| 331 |
-
"model.layers.
|
| 332 |
-
"model.layers.
|
| 333 |
-
"model.layers.
|
| 334 |
-
"model.layers.
|
| 335 |
-
"model.layers.
|
| 336 |
-
"model.layers.
|
| 337 |
-
"model.layers.
|
| 338 |
-
"model.layers.
|
| 339 |
-
"model.layers.
|
| 340 |
-
"model.layers.
|
| 341 |
-
"model.layers.
|
| 342 |
-
"model.layers.
|
| 343 |
-
"model.layers.
|
| 344 |
-
"model.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 345 |
}
|
| 346 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 29540067328
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00006-of-00006.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 31 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 32 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 33 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 34 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 35 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 36 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 42 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 43 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 44 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 45 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 46 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 47 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 48 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 53 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 54 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 55 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 56 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 57 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 58 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 59 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 60 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 64 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 65 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 66 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 67 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 68 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 69 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 70 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 71 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 72 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 75 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 76 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 77 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 78 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 79 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 80 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 81 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 82 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 83 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 84 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 86 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 87 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 88 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 89 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 90 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 91 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 92 |
+
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 93 |
+
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 94 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 95 |
+
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 96 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 97 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 98 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 99 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 100 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 101 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 102 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 103 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 104 |
+
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 105 |
+
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 106 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 107 |
+
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 108 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 109 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 110 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 111 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 112 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 113 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 114 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 115 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 116 |
+
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 117 |
+
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 118 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 119 |
+
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 120 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 121 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 122 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 123 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 124 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 125 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 126 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 127 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 128 |
+
"model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 129 |
+
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 130 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 131 |
+
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 132 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 133 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 134 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 135 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 136 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 137 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 138 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 139 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 140 |
+
"model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 141 |
+
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 142 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 143 |
+
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 144 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 145 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 146 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 147 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 148 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 149 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 150 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 151 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 152 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 153 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 154 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 155 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 156 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 157 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 158 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 159 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 160 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 161 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 162 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 163 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 164 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 165 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 166 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 167 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 168 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 169 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 170 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 171 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 172 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 173 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 174 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 175 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 176 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 177 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 178 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 179 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 180 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 181 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 182 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 183 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 184 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 185 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 186 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 187 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 188 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 189 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 190 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 191 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 192 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 193 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 194 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 195 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 196 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 197 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 198 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 199 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 200 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 201 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
|
| 202 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
|
| 203 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
|
| 204 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
|
| 205 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 206 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 207 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 208 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 209 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 210 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 211 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 212 |
+
"model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 213 |
+
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 214 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 215 |
+
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 216 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 217 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00006.safetensors",
|
| 218 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
|
| 219 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
|
| 220 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00006.safetensors",
|
| 221 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
|
| 222 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00006.safetensors",
|
| 223 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
|
| 224 |
+
"model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 225 |
+
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 226 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 227 |
+
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 228 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 229 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 230 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 231 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 232 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 233 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 234 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 235 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 236 |
+
"model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 237 |
+
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 238 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 239 |
+
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 240 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 241 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 242 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 243 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 244 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 245 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 246 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 247 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 248 |
+
"model.layers.27.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 249 |
+
"model.layers.27.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 250 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 251 |
+
"model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 252 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 253 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 254 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 255 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 256 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 257 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 258 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 259 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 260 |
+
"model.layers.28.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 261 |
+
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 262 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 263 |
+
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 264 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 265 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 266 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 267 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 268 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 269 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 270 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 271 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 272 |
+
"model.layers.29.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 273 |
+
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 274 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 275 |
+
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 276 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 277 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 278 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 279 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 280 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 281 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 282 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 283 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 284 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 285 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 286 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 287 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 288 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 289 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 290 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 291 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 292 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 293 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 294 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 295 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 296 |
+
"model.layers.30.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 297 |
+
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 298 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 299 |
+
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 300 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 301 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 302 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 303 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 304 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 305 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 306 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 307 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 308 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 309 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 310 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 311 |
+
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 312 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 313 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 314 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 315 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 316 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 317 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 318 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 319 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 320 |
+
"model.layers.32.input_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 321 |
+
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
|
| 322 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
|
| 323 |
+
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
|
| 324 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
|
| 325 |
+
"model.layers.32.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 326 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 327 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 328 |
+
"model.layers.32.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 329 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 330 |
+
"model.layers.32.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 331 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 332 |
+
"model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 333 |
+
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 334 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 335 |
+
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 336 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 337 |
+
"model.layers.33.self_attn.k_proj.bias": "model-00004-of-00006.safetensors",
|
| 338 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
|
| 339 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
|
| 340 |
+
"model.layers.33.self_attn.q_proj.bias": "model-00004-of-00006.safetensors",
|
| 341 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
|
| 342 |
+
"model.layers.33.self_attn.v_proj.bias": "model-00004-of-00006.safetensors",
|
| 343 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
|
| 344 |
+
"model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 345 |
+
"model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 346 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 347 |
+
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 348 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 349 |
+
"model.layers.34.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 350 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 351 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 352 |
+
"model.layers.34.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 353 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 354 |
+
"model.layers.34.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 355 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 356 |
+
"model.layers.35.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 357 |
+
"model.layers.35.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 358 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 359 |
+
"model.layers.35.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 360 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 361 |
+
"model.layers.35.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 362 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 363 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 364 |
+
"model.layers.35.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 365 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 366 |
+
"model.layers.35.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 367 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 368 |
+
"model.layers.36.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 369 |
+
"model.layers.36.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 370 |
+
"model.layers.36.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 371 |
+
"model.layers.36.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 372 |
+
"model.layers.36.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 373 |
+
"model.layers.36.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 374 |
+
"model.layers.36.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 375 |
+
"model.layers.36.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 376 |
+
"model.layers.36.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 377 |
+
"model.layers.36.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 378 |
+
"model.layers.36.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 379 |
+
"model.layers.36.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 380 |
+
"model.layers.37.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 381 |
+
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 382 |
+
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 383 |
+
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 384 |
+
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 385 |
+
"model.layers.37.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 386 |
+
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 387 |
+
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 388 |
+
"model.layers.37.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 389 |
+
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 390 |
+
"model.layers.37.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 391 |
+
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 392 |
+
"model.layers.38.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 393 |
+
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 394 |
+
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 395 |
+
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 396 |
+
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 397 |
+
"model.layers.38.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 398 |
+
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 399 |
+
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 400 |
+
"model.layers.38.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 401 |
+
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 402 |
+
"model.layers.38.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 403 |
+
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 404 |
+
"model.layers.39.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 405 |
+
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 406 |
+
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 407 |
+
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 408 |
+
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 409 |
+
"model.layers.39.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 410 |
+
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 411 |
+
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 412 |
+
"model.layers.39.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 413 |
+
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 414 |
+
"model.layers.39.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 415 |
+
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 416 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 417 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 418 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 419 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 420 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 421 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 422 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 423 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 424 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 425 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 426 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 427 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 428 |
+
"model.layers.40.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 429 |
+
"model.layers.40.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 430 |
+
"model.layers.40.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 431 |
+
"model.layers.40.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 432 |
+
"model.layers.40.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 433 |
+
"model.layers.40.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 434 |
+
"model.layers.40.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 435 |
+
"model.layers.40.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 436 |
+
"model.layers.40.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 437 |
+
"model.layers.40.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 438 |
+
"model.layers.40.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 439 |
+
"model.layers.40.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 440 |
+
"model.layers.41.input_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 441 |
+
"model.layers.41.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
|
| 442 |
+
"model.layers.41.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
|
| 443 |
+
"model.layers.41.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
|
| 444 |
+
"model.layers.41.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
|
| 445 |
+
"model.layers.41.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 446 |
+
"model.layers.41.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 447 |
+
"model.layers.41.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 448 |
+
"model.layers.41.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 449 |
+
"model.layers.41.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 450 |
+
"model.layers.41.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 451 |
+
"model.layers.41.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 452 |
+
"model.layers.42.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 453 |
+
"model.layers.42.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 454 |
+
"model.layers.42.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 455 |
+
"model.layers.42.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 456 |
+
"model.layers.42.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 457 |
+
"model.layers.42.self_attn.k_proj.bias": "model-00005-of-00006.safetensors",
|
| 458 |
+
"model.layers.42.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
|
| 459 |
+
"model.layers.42.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
|
| 460 |
+
"model.layers.42.self_attn.q_proj.bias": "model-00005-of-00006.safetensors",
|
| 461 |
+
"model.layers.42.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
|
| 462 |
+
"model.layers.42.self_attn.v_proj.bias": "model-00005-of-00006.safetensors",
|
| 463 |
+
"model.layers.42.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
|
| 464 |
+
"model.layers.43.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 465 |
+
"model.layers.43.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 466 |
+
"model.layers.43.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 467 |
+
"model.layers.43.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 468 |
+
"model.layers.43.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 469 |
+
"model.layers.43.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
| 470 |
+
"model.layers.43.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 471 |
+
"model.layers.43.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 472 |
+
"model.layers.43.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
| 473 |
+
"model.layers.43.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 474 |
+
"model.layers.43.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
| 475 |
+
"model.layers.43.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 476 |
+
"model.layers.44.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 477 |
+
"model.layers.44.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 478 |
+
"model.layers.44.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 479 |
+
"model.layers.44.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 480 |
+
"model.layers.44.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 481 |
+
"model.layers.44.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
| 482 |
+
"model.layers.44.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 483 |
+
"model.layers.44.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 484 |
+
"model.layers.44.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
| 485 |
+
"model.layers.44.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 486 |
+
"model.layers.44.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
| 487 |
+
"model.layers.44.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 488 |
+
"model.layers.45.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 489 |
+
"model.layers.45.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 490 |
+
"model.layers.45.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 491 |
+
"model.layers.45.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 492 |
+
"model.layers.45.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 493 |
+
"model.layers.45.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
| 494 |
+
"model.layers.45.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 495 |
+
"model.layers.45.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 496 |
+
"model.layers.45.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
| 497 |
+
"model.layers.45.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 498 |
+
"model.layers.45.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
| 499 |
+
"model.layers.45.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 500 |
+
"model.layers.46.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 501 |
+
"model.layers.46.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 502 |
+
"model.layers.46.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 503 |
+
"model.layers.46.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 504 |
+
"model.layers.46.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 505 |
+
"model.layers.46.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
| 506 |
+
"model.layers.46.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 507 |
+
"model.layers.46.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 508 |
+
"model.layers.46.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
| 509 |
+
"model.layers.46.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 510 |
+
"model.layers.46.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
| 511 |
+
"model.layers.46.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 512 |
+
"model.layers.47.input_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 513 |
+
"model.layers.47.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
|
| 514 |
+
"model.layers.47.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
|
| 515 |
+
"model.layers.47.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
|
| 516 |
+
"model.layers.47.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
|
| 517 |
+
"model.layers.47.self_attn.k_proj.bias": "model-00006-of-00006.safetensors",
|
| 518 |
+
"model.layers.47.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
|
| 519 |
+
"model.layers.47.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
|
| 520 |
+
"model.layers.47.self_attn.q_proj.bias": "model-00006-of-00006.safetensors",
|
| 521 |
+
"model.layers.47.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
|
| 522 |
+
"model.layers.47.self_attn.v_proj.bias": "model-00006-of-00006.safetensors",
|
| 523 |
+
"model.layers.47.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
|
| 524 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 525 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
|
| 526 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
|
| 527 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
|
| 528 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
|
| 529 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 530 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 531 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 532 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 533 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 534 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 535 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 536 |
+
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 537 |
+
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 538 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 539 |
+
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 540 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 541 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00006.safetensors",
|
| 542 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
|
| 543 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
|
| 544 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00006.safetensors",
|
| 545 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
|
| 546 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00006.safetensors",
|
| 547 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
|
| 548 |
+
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 549 |
+
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 550 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 551 |
+
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 552 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 553 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 554 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 555 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 556 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 557 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 558 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 559 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 560 |
+
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 561 |
+
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 562 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 563 |
+
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 564 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 565 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 566 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 567 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 568 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 569 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 570 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 571 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 572 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 573 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
|
| 574 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
|
| 575 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
|
| 576 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
|
| 577 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00006.safetensors",
|
| 578 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
|
| 579 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
|
| 580 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00006.safetensors",
|
| 581 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
|
| 582 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00006.safetensors",
|
| 583 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
|
| 584 |
+
"model.norm.weight": "model-00006-of-00006.safetensors"
|
| 585 |
}
|
| 586 |
}
|
rng_state_0.pth
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:f068e2025a4f00989e9c03d01c1281f7d1906969b0fbe7319192d985b5de4d49
|
| 3 |
+
size 15984
|
rng_state_1.pth
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 sha256:2120f02ce7a002ef9e970ec506c42eb25f7d875f674566d6ad7c342a0a258acd
|
| 3 |
+
size 15984
|
rng_state_2.pth
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:c78254b86c335260938fb97d27b32bab843db1941a13389d01fefd73eef0201b
|
| 3 |
+
size 15984
|
rng_state_3.pth
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 sha256:610071c273687a048043135ba6e816c86cd8cbc842496954bb1b35ca01c4c382
|
| 3 |
+
size 15984
|
rng_state_4.pth
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 sha256:8edad2884c4e758562a95fef0fcf48f82a9ce39dbace5d1e32bcbfb847c72140
|
| 3 |
+
size 15984
|
rng_state_5.pth
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:f1a41860bf7ca64b413a603bb6d5f036cb9d3c9a7f940c56733ca7e6bfab8afe
|
| 3 |
+
size 15984
|
rng_state_6.pth
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 sha256:258cea0926b92515dd8e0b49a91e9c7c6562597efa3422fce84c690cdf7c126c
|
| 3 |
+
size 15984
|
rng_state_7.pth
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:ca741f170ce54d6b6c5971457ec6506474163b21edaa3fbaa4e5285d89d229b1
|
| 3 |
+
size 15984
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed96bbe4d84037e4c18f95733da1d2d5bb47c4402c4d667156d5ed1ff760dfb0
|
| 3 |
size 1064
|
tokenizer_config.json
CHANGED
|
@@ -185,7 +185,7 @@
|
|
| 185 |
"clean_up_tokenization_spaces": false,
|
| 186 |
"eos_token": "<｜end▁of▁sentence｜>",
|
| 187 |
"legacy": true,
|
| 188 |
-
"model_max_length":
|
| 189 |
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
"padding_side": "left",
|
| 191 |
"sp_model_kwargs": {},
|
|
|
|
| 185 |
"clean_up_tokenization_spaces": false,
|
| 186 |
"eos_token": "<｜end▁of▁sentence｜>",
|
| 187 |
"legacy": true,
|
| 188 |
+
"model_max_length": 16000,
|
| 189 |
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
"padding_side": "left",
|
| 191 |
"sp_model_kwargs": {},
|
trainer_state.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
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:e58fa949caa5f03669bd0d8bb18548b753852f3f732f36df28a00d4b854effa3
|
| 3 |
+
size 8440
|