File size: 30,884 Bytes
bcf87a6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 |
{
"metadata": {
"total_size": 22205644800
},
"weight_map": {
"lm_head.weight": "model-00005-of-00005.safetensors",
"transformer.h.0.input_layernorm.bias": "model-00001-of-00005.safetensors",
"transformer.h.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
"transformer.h.0.mlp.downscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.0.mlp.upscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.0.self_attention.dense.weight": "model-00001-of-00005.safetensors",
"transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
"transformer.h.1.input_layernorm.bias": "model-00001-of-00005.safetensors",
"transformer.h.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
"transformer.h.1.mlp.downscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.1.mlp.upscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.1.self_attention.dense.weight": "model-00001-of-00005.safetensors",
"transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
"transformer.h.10.input_layernorm.bias": "model-00001-of-00005.safetensors",
"transformer.h.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
"transformer.h.10.mlp.downscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.10.mlp.upscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.10.self_attention.dense.weight": "model-00001-of-00005.safetensors",
"transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
"transformer.h.11.input_layernorm.bias": "model-00001-of-00005.safetensors",
"transformer.h.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
"transformer.h.11.mlp.downscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.11.mlp.upscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.11.self_attention.dense.weight": "model-00001-of-00005.safetensors",
"transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
"transformer.h.12.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.12.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.12.mlp.upscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.12.self_attention.dense.weight": "model-00001-of-00005.safetensors",
"transformer.h.12.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
"transformer.h.13.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.13.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.13.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.13.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.13.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.14.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.14.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.14.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.14.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.14.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.15.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.15.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.15.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.15.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.16.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.16.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.16.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.16.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.17.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.17.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.17.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.17.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.18.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.18.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.18.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.18.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.19.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.19.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.19.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.19.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.2.input_layernorm.bias": "model-00001-of-00005.safetensors",
"transformer.h.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
"transformer.h.2.mlp.downscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.2.mlp.upscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.2.self_attention.dense.weight": "model-00001-of-00005.safetensors",
"transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
"transformer.h.20.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.20.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.20.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.20.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.20.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.21.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.21.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.21.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.21.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.21.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.21.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.22.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.22.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.22.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.22.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.22.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.22.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.23.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.23.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.23.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.23.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.23.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.24.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.24.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.24.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.24.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.24.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.24.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.25.input_layernorm.bias": "model-00002-of-00005.safetensors",
"transformer.h.25.input_layernorm.weight": "model-00002-of-00005.safetensors",
"transformer.h.25.mlp.downscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.25.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.25.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.25.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.26.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.26.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.26.mlp.upscale.weight": "model-00002-of-00005.safetensors",
"transformer.h.26.self_attention.dense.weight": "model-00002-of-00005.safetensors",
"transformer.h.26.self_attention.query_key_value.weight": "model-00002-of-00005.safetensors",
"transformer.h.27.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.27.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.27.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.27.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.27.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.28.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.28.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.28.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.28.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.28.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.29.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.29.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.29.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.29.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.29.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.3.input_layernorm.bias": "model-00001-of-00005.safetensors",
"transformer.h.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
"transformer.h.3.mlp.downscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.3.mlp.upscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.3.self_attention.dense.weight": "model-00001-of-00005.safetensors",
"transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
"transformer.h.30.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.30.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.30.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.30.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.30.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.30.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.31.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.31.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.31.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.31.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.31.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.31.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.32.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.32.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.32.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.32.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.32.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.32.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.33.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.33.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.33.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.33.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.33.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.33.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.34.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.34.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.34.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.34.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.34.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.34.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.35.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.35.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.35.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.35.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.35.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.35.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.36.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.36.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.36.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.36.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.36.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.36.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.37.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.37.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.37.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.37.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.37.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.37.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.38.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.38.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.38.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.38.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.38.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.38.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.39.input_layernorm.bias": "model-00003-of-00005.safetensors",
"transformer.h.39.input_layernorm.weight": "model-00003-of-00005.safetensors",
"transformer.h.39.mlp.downscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.39.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.39.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.39.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.4.input_layernorm.bias": "model-00001-of-00005.safetensors",
"transformer.h.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
"transformer.h.4.mlp.downscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.4.mlp.upscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.4.self_attention.dense.weight": "model-00001-of-00005.safetensors",
"transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
"transformer.h.40.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.40.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.40.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.40.mlp.upscale.weight": "model-00003-of-00005.safetensors",
"transformer.h.40.self_attention.dense.weight": "model-00003-of-00005.safetensors",
"transformer.h.40.self_attention.query_key_value.weight": "model-00003-of-00005.safetensors",
"transformer.h.41.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.41.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.41.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.41.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.41.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.41.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.42.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.42.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.42.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.42.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.42.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.42.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.43.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.43.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.43.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.43.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.43.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.43.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.44.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.44.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.44.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.44.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.44.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.44.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.45.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.45.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.45.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.45.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.45.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.45.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.46.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.46.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.46.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.46.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.46.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.46.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.47.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.47.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.47.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.47.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.47.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.47.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.48.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.48.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.48.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.48.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.48.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.48.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.49.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.49.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.49.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.49.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.49.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.49.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.5.input_layernorm.bias": "model-00001-of-00005.safetensors",
"transformer.h.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
"transformer.h.5.mlp.downscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.5.mlp.upscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.5.self_attention.dense.weight": "model-00001-of-00005.safetensors",
"transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
"transformer.h.50.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.50.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.50.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.50.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.50.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.50.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.51.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.51.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.51.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.51.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.51.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.51.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.52.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.52.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.52.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.52.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.52.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.52.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.53.input_layernorm.bias": "model-00004-of-00005.safetensors",
"transformer.h.53.input_layernorm.weight": "model-00004-of-00005.safetensors",
"transformer.h.53.mlp.downscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.53.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.53.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.53.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.54.input_layernorm.bias": "model-00005-of-00005.safetensors",
"transformer.h.54.input_layernorm.weight": "model-00005-of-00005.safetensors",
"transformer.h.54.mlp.downscale.weight": "model-00005-of-00005.safetensors",
"transformer.h.54.mlp.upscale.weight": "model-00004-of-00005.safetensors",
"transformer.h.54.self_attention.dense.weight": "model-00004-of-00005.safetensors",
"transformer.h.54.self_attention.query_key_value.weight": "model-00004-of-00005.safetensors",
"transformer.h.55.input_layernorm.bias": "model-00005-of-00005.safetensors",
"transformer.h.55.input_layernorm.weight": "model-00005-of-00005.safetensors",
"transformer.h.55.mlp.downscale.weight": "model-00005-of-00005.safetensors",
"transformer.h.55.mlp.upscale.weight": "model-00005-of-00005.safetensors",
"transformer.h.55.self_attention.dense.weight": "model-00005-of-00005.safetensors",
"transformer.h.55.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
"transformer.h.56.input_layernorm.bias": "model-00005-of-00005.safetensors",
"transformer.h.56.input_layernorm.weight": "model-00005-of-00005.safetensors",
"transformer.h.56.mlp.downscale.weight": "model-00005-of-00005.safetensors",
"transformer.h.56.mlp.upscale.weight": "model-00005-of-00005.safetensors",
"transformer.h.56.self_attention.dense.weight": "model-00005-of-00005.safetensors",
"transformer.h.56.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
"transformer.h.57.input_layernorm.bias": "model-00005-of-00005.safetensors",
"transformer.h.57.input_layernorm.weight": "model-00005-of-00005.safetensors",
"transformer.h.57.mlp.downscale.weight": "model-00005-of-00005.safetensors",
"transformer.h.57.mlp.upscale.weight": "model-00005-of-00005.safetensors",
"transformer.h.57.self_attention.dense.weight": "model-00005-of-00005.safetensors",
"transformer.h.57.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
"transformer.h.58.input_layernorm.bias": "model-00005-of-00005.safetensors",
"transformer.h.58.input_layernorm.weight": "model-00005-of-00005.safetensors",
"transformer.h.58.mlp.downscale.weight": "model-00005-of-00005.safetensors",
"transformer.h.58.mlp.upscale.weight": "model-00005-of-00005.safetensors",
"transformer.h.58.self_attention.dense.weight": "model-00005-of-00005.safetensors",
"transformer.h.58.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
"transformer.h.59.input_layernorm.bias": "model-00005-of-00005.safetensors",
"transformer.h.59.input_layernorm.weight": "model-00005-of-00005.safetensors",
"transformer.h.59.mlp.downscale.weight": "model-00005-of-00005.safetensors",
"transformer.h.59.mlp.upscale.weight": "model-00005-of-00005.safetensors",
"transformer.h.59.self_attention.dense.weight": "model-00005-of-00005.safetensors",
"transformer.h.59.self_attention.query_key_value.weight": "model-00005-of-00005.safetensors",
"transformer.h.6.input_layernorm.bias": "model-00001-of-00005.safetensors",
"transformer.h.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
"transformer.h.6.mlp.downscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.6.mlp.upscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.6.self_attention.dense.weight": "model-00001-of-00005.safetensors",
"transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
"transformer.h.7.input_layernorm.bias": "model-00001-of-00005.safetensors",
"transformer.h.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
"transformer.h.7.mlp.downscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.7.mlp.upscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.7.self_attention.dense.weight": "model-00001-of-00005.safetensors",
"transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
"transformer.h.8.input_layernorm.bias": "model-00001-of-00005.safetensors",
"transformer.h.8.input_layernorm.weight": "model-00001-of-00005.safetensors",
"transformer.h.8.mlp.downscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.8.mlp.upscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.8.self_attention.dense.weight": "model-00001-of-00005.safetensors",
"transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
"transformer.h.9.input_layernorm.bias": "model-00001-of-00005.safetensors",
"transformer.h.9.input_layernorm.weight": "model-00001-of-00005.safetensors",
"transformer.h.9.mlp.downscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.9.mlp.upscale.weight": "model-00001-of-00005.safetensors",
"transformer.h.9.self_attention.dense.weight": "model-00001-of-00005.safetensors",
"transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00005.safetensors",
"transformer.ln_f.bias": "model-00005-of-00005.safetensors",
"transformer.ln_f.weight": "model-00005-of-00005.safetensors",
"transformer.word_embeddings.weight": "model-00001-of-00005.safetensors"
}
}
|