File size: 39,445 Bytes
2d015c3 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 |
{
"metadata": {
"total_size": 11793268736
},
"weight_map": {
"embeddings.cls_token": "model-00001-of-00003.safetensors",
"embeddings.mask_token": "model-00001-of-00003.safetensors",
"embeddings.patch_embeddings.projection.bias": "model-00001-of-00003.safetensors",
"embeddings.patch_embeddings.projection.weight": "model-00001-of-00003.safetensors",
"embeddings.position_embeddings": "model-00001-of-00003.safetensors",
"encoder.layer.0.attention.attention.key.bias": "model-00001-of-00003.safetensors",
"encoder.layer.0.attention.attention.key.weight": "model-00001-of-00003.safetensors",
"encoder.layer.0.attention.attention.query.bias": "model-00001-of-00003.safetensors",
"encoder.layer.0.attention.attention.query.weight": "model-00001-of-00003.safetensors",
"encoder.layer.0.attention.attention.value.bias": "model-00001-of-00003.safetensors",
"encoder.layer.0.attention.attention.value.weight": "model-00001-of-00003.safetensors",
"encoder.layer.0.attention.output.dense.bias": "model-00001-of-00003.safetensors",
"encoder.layer.0.attention.output.dense.weight": "model-00001-of-00003.safetensors",
"encoder.layer.0.layer_scale1.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.0.layer_scale2.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.0.mlp.weights_in.bias": "model-00001-of-00003.safetensors",
"encoder.layer.0.mlp.weights_in.weight": "model-00001-of-00003.safetensors",
"encoder.layer.0.mlp.weights_out.bias": "model-00001-of-00003.safetensors",
"encoder.layer.0.mlp.weights_out.weight": "model-00001-of-00003.safetensors",
"encoder.layer.0.norm1.bias": "model-00001-of-00003.safetensors",
"encoder.layer.0.norm1.weight": "model-00001-of-00003.safetensors",
"encoder.layer.0.norm2.bias": "model-00001-of-00003.safetensors",
"encoder.layer.0.norm2.weight": "model-00001-of-00003.safetensors",
"encoder.layer.1.attention.attention.key.bias": "model-00001-of-00003.safetensors",
"encoder.layer.1.attention.attention.key.weight": "model-00001-of-00003.safetensors",
"encoder.layer.1.attention.attention.query.bias": "model-00001-of-00003.safetensors",
"encoder.layer.1.attention.attention.query.weight": "model-00001-of-00003.safetensors",
"encoder.layer.1.attention.attention.value.bias": "model-00001-of-00003.safetensors",
"encoder.layer.1.attention.attention.value.weight": "model-00001-of-00003.safetensors",
"encoder.layer.1.attention.output.dense.bias": "model-00001-of-00003.safetensors",
"encoder.layer.1.attention.output.dense.weight": "model-00001-of-00003.safetensors",
"encoder.layer.1.layer_scale1.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.1.layer_scale2.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.1.mlp.weights_in.bias": "model-00001-of-00003.safetensors",
"encoder.layer.1.mlp.weights_in.weight": "model-00001-of-00003.safetensors",
"encoder.layer.1.mlp.weights_out.bias": "model-00001-of-00003.safetensors",
"encoder.layer.1.mlp.weights_out.weight": "model-00001-of-00003.safetensors",
"encoder.layer.1.norm1.bias": "model-00001-of-00003.safetensors",
"encoder.layer.1.norm1.weight": "model-00001-of-00003.safetensors",
"encoder.layer.1.norm2.bias": "model-00001-of-00003.safetensors",
"encoder.layer.1.norm2.weight": "model-00001-of-00003.safetensors",
"encoder.layer.10.attention.attention.key.bias": "model-00001-of-00003.safetensors",
"encoder.layer.10.attention.attention.key.weight": "model-00001-of-00003.safetensors",
"encoder.layer.10.attention.attention.query.bias": "model-00001-of-00003.safetensors",
"encoder.layer.10.attention.attention.query.weight": "model-00001-of-00003.safetensors",
"encoder.layer.10.attention.attention.value.bias": "model-00001-of-00003.safetensors",
"encoder.layer.10.attention.attention.value.weight": "model-00001-of-00003.safetensors",
"encoder.layer.10.attention.output.dense.bias": "model-00001-of-00003.safetensors",
"encoder.layer.10.attention.output.dense.weight": "model-00001-of-00003.safetensors",
"encoder.layer.10.layer_scale1.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.10.layer_scale2.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.10.mlp.weights_in.bias": "model-00001-of-00003.safetensors",
"encoder.layer.10.mlp.weights_in.weight": "model-00001-of-00003.safetensors",
"encoder.layer.10.mlp.weights_out.bias": "model-00001-of-00003.safetensors",
"encoder.layer.10.mlp.weights_out.weight": "model-00001-of-00003.safetensors",
"encoder.layer.10.norm1.bias": "model-00001-of-00003.safetensors",
"encoder.layer.10.norm1.weight": "model-00001-of-00003.safetensors",
"encoder.layer.10.norm2.bias": "model-00001-of-00003.safetensors",
"encoder.layer.10.norm2.weight": "model-00001-of-00003.safetensors",
"encoder.layer.11.attention.attention.key.bias": "model-00002-of-00003.safetensors",
"encoder.layer.11.attention.attention.key.weight": "model-00002-of-00003.safetensors",
"encoder.layer.11.attention.attention.query.bias": "model-00002-of-00003.safetensors",
"encoder.layer.11.attention.attention.query.weight": "model-00002-of-00003.safetensors",
"encoder.layer.11.attention.attention.value.bias": "model-00002-of-00003.safetensors",
"encoder.layer.11.attention.attention.value.weight": "model-00002-of-00003.safetensors",
"encoder.layer.11.attention.output.dense.bias": "model-00002-of-00003.safetensors",
"encoder.layer.11.attention.output.dense.weight": "model-00002-of-00003.safetensors",
"encoder.layer.11.layer_scale1.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.11.layer_scale2.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.11.mlp.weights_in.bias": "model-00002-of-00003.safetensors",
"encoder.layer.11.mlp.weights_in.weight": "model-00002-of-00003.safetensors",
"encoder.layer.11.mlp.weights_out.bias": "model-00002-of-00003.safetensors",
"encoder.layer.11.mlp.weights_out.weight": "model-00002-of-00003.safetensors",
"encoder.layer.11.norm1.bias": "model-00001-of-00003.safetensors",
"encoder.layer.11.norm1.weight": "model-00001-of-00003.safetensors",
"encoder.layer.11.norm2.bias": "model-00002-of-00003.safetensors",
"encoder.layer.11.norm2.weight": "model-00002-of-00003.safetensors",
"encoder.layer.12.attention.attention.key.bias": "model-00002-of-00003.safetensors",
"encoder.layer.12.attention.attention.key.weight": "model-00002-of-00003.safetensors",
"encoder.layer.12.attention.attention.query.bias": "model-00002-of-00003.safetensors",
"encoder.layer.12.attention.attention.query.weight": "model-00002-of-00003.safetensors",
"encoder.layer.12.attention.attention.value.bias": "model-00002-of-00003.safetensors",
"encoder.layer.12.attention.attention.value.weight": "model-00002-of-00003.safetensors",
"encoder.layer.12.attention.output.dense.bias": "model-00002-of-00003.safetensors",
"encoder.layer.12.attention.output.dense.weight": "model-00002-of-00003.safetensors",
"encoder.layer.12.layer_scale1.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.12.layer_scale2.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.12.mlp.weights_in.bias": "model-00002-of-00003.safetensors",
"encoder.layer.12.mlp.weights_in.weight": "model-00002-of-00003.safetensors",
"encoder.layer.12.mlp.weights_out.bias": "model-00002-of-00003.safetensors",
"encoder.layer.12.mlp.weights_out.weight": "model-00002-of-00003.safetensors",
"encoder.layer.12.norm1.bias": "model-00002-of-00003.safetensors",
"encoder.layer.12.norm1.weight": "model-00002-of-00003.safetensors",
"encoder.layer.12.norm2.bias": "model-00002-of-00003.safetensors",
"encoder.layer.12.norm2.weight": "model-00002-of-00003.safetensors",
"encoder.layer.13.attention.attention.key.bias": "model-00002-of-00003.safetensors",
"encoder.layer.13.attention.attention.key.weight": "model-00002-of-00003.safetensors",
"encoder.layer.13.attention.attention.query.bias": "model-00002-of-00003.safetensors",
"encoder.layer.13.attention.attention.query.weight": "model-00002-of-00003.safetensors",
"encoder.layer.13.attention.attention.value.bias": "model-00002-of-00003.safetensors",
"encoder.layer.13.attention.attention.value.weight": "model-00002-of-00003.safetensors",
"encoder.layer.13.attention.output.dense.bias": "model-00002-of-00003.safetensors",
"encoder.layer.13.attention.output.dense.weight": "model-00002-of-00003.safetensors",
"encoder.layer.13.layer_scale1.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.13.layer_scale2.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.13.mlp.weights_in.bias": "model-00002-of-00003.safetensors",
"encoder.layer.13.mlp.weights_in.weight": "model-00002-of-00003.safetensors",
"encoder.layer.13.mlp.weights_out.bias": "model-00002-of-00003.safetensors",
"encoder.layer.13.mlp.weights_out.weight": "model-00002-of-00003.safetensors",
"encoder.layer.13.norm1.bias": "model-00002-of-00003.safetensors",
"encoder.layer.13.norm1.weight": "model-00002-of-00003.safetensors",
"encoder.layer.13.norm2.bias": "model-00002-of-00003.safetensors",
"encoder.layer.13.norm2.weight": "model-00002-of-00003.safetensors",
"encoder.layer.14.attention.attention.key.bias": "model-00002-of-00003.safetensors",
"encoder.layer.14.attention.attention.key.weight": "model-00002-of-00003.safetensors",
"encoder.layer.14.attention.attention.query.bias": "model-00002-of-00003.safetensors",
"encoder.layer.14.attention.attention.query.weight": "model-00002-of-00003.safetensors",
"encoder.layer.14.attention.attention.value.bias": "model-00002-of-00003.safetensors",
"encoder.layer.14.attention.attention.value.weight": "model-00002-of-00003.safetensors",
"encoder.layer.14.attention.output.dense.bias": "model-00002-of-00003.safetensors",
"encoder.layer.14.attention.output.dense.weight": "model-00002-of-00003.safetensors",
"encoder.layer.14.layer_scale1.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.14.layer_scale2.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.14.mlp.weights_in.bias": "model-00002-of-00003.safetensors",
"encoder.layer.14.mlp.weights_in.weight": "model-00002-of-00003.safetensors",
"encoder.layer.14.mlp.weights_out.bias": "model-00002-of-00003.safetensors",
"encoder.layer.14.mlp.weights_out.weight": "model-00002-of-00003.safetensors",
"encoder.layer.14.norm1.bias": "model-00002-of-00003.safetensors",
"encoder.layer.14.norm1.weight": "model-00002-of-00003.safetensors",
"encoder.layer.14.norm2.bias": "model-00002-of-00003.safetensors",
"encoder.layer.14.norm2.weight": "model-00002-of-00003.safetensors",
"encoder.layer.15.attention.attention.key.bias": "model-00002-of-00003.safetensors",
"encoder.layer.15.attention.attention.key.weight": "model-00002-of-00003.safetensors",
"encoder.layer.15.attention.attention.query.bias": "model-00002-of-00003.safetensors",
"encoder.layer.15.attention.attention.query.weight": "model-00002-of-00003.safetensors",
"encoder.layer.15.attention.attention.value.bias": "model-00002-of-00003.safetensors",
"encoder.layer.15.attention.attention.value.weight": "model-00002-of-00003.safetensors",
"encoder.layer.15.attention.output.dense.bias": "model-00002-of-00003.safetensors",
"encoder.layer.15.attention.output.dense.weight": "model-00002-of-00003.safetensors",
"encoder.layer.15.layer_scale1.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.15.layer_scale2.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.15.mlp.weights_in.bias": "model-00002-of-00003.safetensors",
"encoder.layer.15.mlp.weights_in.weight": "model-00002-of-00003.safetensors",
"encoder.layer.15.mlp.weights_out.bias": "model-00002-of-00003.safetensors",
"encoder.layer.15.mlp.weights_out.weight": "model-00002-of-00003.safetensors",
"encoder.layer.15.norm1.bias": "model-00002-of-00003.safetensors",
"encoder.layer.15.norm1.weight": "model-00002-of-00003.safetensors",
"encoder.layer.15.norm2.bias": "model-00002-of-00003.safetensors",
"encoder.layer.15.norm2.weight": "model-00002-of-00003.safetensors",
"encoder.layer.16.attention.attention.key.bias": "model-00002-of-00003.safetensors",
"encoder.layer.16.attention.attention.key.weight": "model-00002-of-00003.safetensors",
"encoder.layer.16.attention.attention.query.bias": "model-00002-of-00003.safetensors",
"encoder.layer.16.attention.attention.query.weight": "model-00002-of-00003.safetensors",
"encoder.layer.16.attention.attention.value.bias": "model-00002-of-00003.safetensors",
"encoder.layer.16.attention.attention.value.weight": "model-00002-of-00003.safetensors",
"encoder.layer.16.attention.output.dense.bias": "model-00002-of-00003.safetensors",
"encoder.layer.16.attention.output.dense.weight": "model-00002-of-00003.safetensors",
"encoder.layer.16.layer_scale1.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.16.layer_scale2.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.16.mlp.weights_in.bias": "model-00002-of-00003.safetensors",
"encoder.layer.16.mlp.weights_in.weight": "model-00002-of-00003.safetensors",
"encoder.layer.16.mlp.weights_out.bias": "model-00002-of-00003.safetensors",
"encoder.layer.16.mlp.weights_out.weight": "model-00002-of-00003.safetensors",
"encoder.layer.16.norm1.bias": "model-00002-of-00003.safetensors",
"encoder.layer.16.norm1.weight": "model-00002-of-00003.safetensors",
"encoder.layer.16.norm2.bias": "model-00002-of-00003.safetensors",
"encoder.layer.16.norm2.weight": "model-00002-of-00003.safetensors",
"encoder.layer.17.attention.attention.key.bias": "model-00002-of-00003.safetensors",
"encoder.layer.17.attention.attention.key.weight": "model-00002-of-00003.safetensors",
"encoder.layer.17.attention.attention.query.bias": "model-00002-of-00003.safetensors",
"encoder.layer.17.attention.attention.query.weight": "model-00002-of-00003.safetensors",
"encoder.layer.17.attention.attention.value.bias": "model-00002-of-00003.safetensors",
"encoder.layer.17.attention.attention.value.weight": "model-00002-of-00003.safetensors",
"encoder.layer.17.attention.output.dense.bias": "model-00002-of-00003.safetensors",
"encoder.layer.17.attention.output.dense.weight": "model-00002-of-00003.safetensors",
"encoder.layer.17.layer_scale1.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.17.layer_scale2.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.17.mlp.weights_in.bias": "model-00002-of-00003.safetensors",
"encoder.layer.17.mlp.weights_in.weight": "model-00002-of-00003.safetensors",
"encoder.layer.17.mlp.weights_out.bias": "model-00002-of-00003.safetensors",
"encoder.layer.17.mlp.weights_out.weight": "model-00002-of-00003.safetensors",
"encoder.layer.17.norm1.bias": "model-00002-of-00003.safetensors",
"encoder.layer.17.norm1.weight": "model-00002-of-00003.safetensors",
"encoder.layer.17.norm2.bias": "model-00002-of-00003.safetensors",
"encoder.layer.17.norm2.weight": "model-00002-of-00003.safetensors",
"encoder.layer.18.attention.attention.key.bias": "model-00002-of-00003.safetensors",
"encoder.layer.18.attention.attention.key.weight": "model-00002-of-00003.safetensors",
"encoder.layer.18.attention.attention.query.bias": "model-00002-of-00003.safetensors",
"encoder.layer.18.attention.attention.query.weight": "model-00002-of-00003.safetensors",
"encoder.layer.18.attention.attention.value.bias": "model-00002-of-00003.safetensors",
"encoder.layer.18.attention.attention.value.weight": "model-00002-of-00003.safetensors",
"encoder.layer.18.attention.output.dense.bias": "model-00002-of-00003.safetensors",
"encoder.layer.18.attention.output.dense.weight": "model-00002-of-00003.safetensors",
"encoder.layer.18.layer_scale1.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.18.layer_scale2.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.18.mlp.weights_in.bias": "model-00002-of-00003.safetensors",
"encoder.layer.18.mlp.weights_in.weight": "model-00002-of-00003.safetensors",
"encoder.layer.18.mlp.weights_out.bias": "model-00002-of-00003.safetensors",
"encoder.layer.18.mlp.weights_out.weight": "model-00002-of-00003.safetensors",
"encoder.layer.18.norm1.bias": "model-00002-of-00003.safetensors",
"encoder.layer.18.norm1.weight": "model-00002-of-00003.safetensors",
"encoder.layer.18.norm2.bias": "model-00002-of-00003.safetensors",
"encoder.layer.18.norm2.weight": "model-00002-of-00003.safetensors",
"encoder.layer.19.attention.attention.key.bias": "model-00002-of-00003.safetensors",
"encoder.layer.19.attention.attention.key.weight": "model-00002-of-00003.safetensors",
"encoder.layer.19.attention.attention.query.bias": "model-00002-of-00003.safetensors",
"encoder.layer.19.attention.attention.query.weight": "model-00002-of-00003.safetensors",
"encoder.layer.19.attention.attention.value.bias": "model-00002-of-00003.safetensors",
"encoder.layer.19.attention.attention.value.weight": "model-00002-of-00003.safetensors",
"encoder.layer.19.attention.output.dense.bias": "model-00002-of-00003.safetensors",
"encoder.layer.19.attention.output.dense.weight": "model-00002-of-00003.safetensors",
"encoder.layer.19.layer_scale1.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.19.layer_scale2.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.19.mlp.weights_in.bias": "model-00002-of-00003.safetensors",
"encoder.layer.19.mlp.weights_in.weight": "model-00002-of-00003.safetensors",
"encoder.layer.19.mlp.weights_out.bias": "model-00002-of-00003.safetensors",
"encoder.layer.19.mlp.weights_out.weight": "model-00002-of-00003.safetensors",
"encoder.layer.19.norm1.bias": "model-00002-of-00003.safetensors",
"encoder.layer.19.norm1.weight": "model-00002-of-00003.safetensors",
"encoder.layer.19.norm2.bias": "model-00002-of-00003.safetensors",
"encoder.layer.19.norm2.weight": "model-00002-of-00003.safetensors",
"encoder.layer.2.attention.attention.key.bias": "model-00001-of-00003.safetensors",
"encoder.layer.2.attention.attention.key.weight": "model-00001-of-00003.safetensors",
"encoder.layer.2.attention.attention.query.bias": "model-00001-of-00003.safetensors",
"encoder.layer.2.attention.attention.query.weight": "model-00001-of-00003.safetensors",
"encoder.layer.2.attention.attention.value.bias": "model-00001-of-00003.safetensors",
"encoder.layer.2.attention.attention.value.weight": "model-00001-of-00003.safetensors",
"encoder.layer.2.attention.output.dense.bias": "model-00001-of-00003.safetensors",
"encoder.layer.2.attention.output.dense.weight": "model-00001-of-00003.safetensors",
"encoder.layer.2.layer_scale1.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.2.layer_scale2.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.2.mlp.weights_in.bias": "model-00001-of-00003.safetensors",
"encoder.layer.2.mlp.weights_in.weight": "model-00001-of-00003.safetensors",
"encoder.layer.2.mlp.weights_out.bias": "model-00001-of-00003.safetensors",
"encoder.layer.2.mlp.weights_out.weight": "model-00001-of-00003.safetensors",
"encoder.layer.2.norm1.bias": "model-00001-of-00003.safetensors",
"encoder.layer.2.norm1.weight": "model-00001-of-00003.safetensors",
"encoder.layer.2.norm2.bias": "model-00001-of-00003.safetensors",
"encoder.layer.2.norm2.weight": "model-00001-of-00003.safetensors",
"encoder.layer.20.attention.attention.key.bias": "model-00002-of-00003.safetensors",
"encoder.layer.20.attention.attention.key.weight": "model-00002-of-00003.safetensors",
"encoder.layer.20.attention.attention.query.bias": "model-00002-of-00003.safetensors",
"encoder.layer.20.attention.attention.query.weight": "model-00002-of-00003.safetensors",
"encoder.layer.20.attention.attention.value.bias": "model-00002-of-00003.safetensors",
"encoder.layer.20.attention.attention.value.weight": "model-00002-of-00003.safetensors",
"encoder.layer.20.attention.output.dense.bias": "model-00002-of-00003.safetensors",
"encoder.layer.20.attention.output.dense.weight": "model-00002-of-00003.safetensors",
"encoder.layer.20.layer_scale1.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.20.layer_scale2.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.20.mlp.weights_in.bias": "model-00002-of-00003.safetensors",
"encoder.layer.20.mlp.weights_in.weight": "model-00002-of-00003.safetensors",
"encoder.layer.20.mlp.weights_out.bias": "model-00002-of-00003.safetensors",
"encoder.layer.20.mlp.weights_out.weight": "model-00002-of-00003.safetensors",
"encoder.layer.20.norm1.bias": "model-00002-of-00003.safetensors",
"encoder.layer.20.norm1.weight": "model-00002-of-00003.safetensors",
"encoder.layer.20.norm2.bias": "model-00002-of-00003.safetensors",
"encoder.layer.20.norm2.weight": "model-00002-of-00003.safetensors",
"encoder.layer.21.attention.attention.key.bias": "model-00002-of-00003.safetensors",
"encoder.layer.21.attention.attention.key.weight": "model-00002-of-00003.safetensors",
"encoder.layer.21.attention.attention.query.bias": "model-00002-of-00003.safetensors",
"encoder.layer.21.attention.attention.query.weight": "model-00002-of-00003.safetensors",
"encoder.layer.21.attention.attention.value.bias": "model-00002-of-00003.safetensors",
"encoder.layer.21.attention.attention.value.weight": "model-00002-of-00003.safetensors",
"encoder.layer.21.attention.output.dense.bias": "model-00002-of-00003.safetensors",
"encoder.layer.21.attention.output.dense.weight": "model-00002-of-00003.safetensors",
"encoder.layer.21.layer_scale1.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.21.layer_scale2.lambda1": "model-00002-of-00003.safetensors",
"encoder.layer.21.mlp.weights_in.bias": "model-00002-of-00003.safetensors",
"encoder.layer.21.mlp.weights_in.weight": "model-00002-of-00003.safetensors",
"encoder.layer.21.mlp.weights_out.bias": "model-00002-of-00003.safetensors",
"encoder.layer.21.mlp.weights_out.weight": "model-00002-of-00003.safetensors",
"encoder.layer.21.norm1.bias": "model-00002-of-00003.safetensors",
"encoder.layer.21.norm1.weight": "model-00002-of-00003.safetensors",
"encoder.layer.21.norm2.bias": "model-00002-of-00003.safetensors",
"encoder.layer.21.norm2.weight": "model-00002-of-00003.safetensors",
"encoder.layer.22.attention.attention.key.bias": "model-00003-of-00003.safetensors",
"encoder.layer.22.attention.attention.key.weight": "model-00003-of-00003.safetensors",
"encoder.layer.22.attention.attention.query.bias": "model-00003-of-00003.safetensors",
"encoder.layer.22.attention.attention.query.weight": "model-00003-of-00003.safetensors",
"encoder.layer.22.attention.attention.value.bias": "model-00003-of-00003.safetensors",
"encoder.layer.22.attention.attention.value.weight": "model-00003-of-00003.safetensors",
"encoder.layer.22.attention.output.dense.bias": "model-00003-of-00003.safetensors",
"encoder.layer.22.attention.output.dense.weight": "model-00003-of-00003.safetensors",
"encoder.layer.22.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
"encoder.layer.22.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
"encoder.layer.22.mlp.weights_in.bias": "model-00003-of-00003.safetensors",
"encoder.layer.22.mlp.weights_in.weight": "model-00003-of-00003.safetensors",
"encoder.layer.22.mlp.weights_out.bias": "model-00003-of-00003.safetensors",
"encoder.layer.22.mlp.weights_out.weight": "model-00003-of-00003.safetensors",
"encoder.layer.22.norm1.bias": "model-00002-of-00003.safetensors",
"encoder.layer.22.norm1.weight": "model-00002-of-00003.safetensors",
"encoder.layer.22.norm2.bias": "model-00003-of-00003.safetensors",
"encoder.layer.22.norm2.weight": "model-00003-of-00003.safetensors",
"encoder.layer.23.attention.attention.key.bias": "model-00003-of-00003.safetensors",
"encoder.layer.23.attention.attention.key.weight": "model-00003-of-00003.safetensors",
"encoder.layer.23.attention.attention.query.bias": "model-00003-of-00003.safetensors",
"encoder.layer.23.attention.attention.query.weight": "model-00003-of-00003.safetensors",
"encoder.layer.23.attention.attention.value.bias": "model-00003-of-00003.safetensors",
"encoder.layer.23.attention.attention.value.weight": "model-00003-of-00003.safetensors",
"encoder.layer.23.attention.output.dense.bias": "model-00003-of-00003.safetensors",
"encoder.layer.23.attention.output.dense.weight": "model-00003-of-00003.safetensors",
"encoder.layer.23.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
"encoder.layer.23.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
"encoder.layer.23.mlp.weights_in.bias": "model-00003-of-00003.safetensors",
"encoder.layer.23.mlp.weights_in.weight": "model-00003-of-00003.safetensors",
"encoder.layer.23.mlp.weights_out.bias": "model-00003-of-00003.safetensors",
"encoder.layer.23.mlp.weights_out.weight": "model-00003-of-00003.safetensors",
"encoder.layer.23.norm1.bias": "model-00003-of-00003.safetensors",
"encoder.layer.23.norm1.weight": "model-00003-of-00003.safetensors",
"encoder.layer.23.norm2.bias": "model-00003-of-00003.safetensors",
"encoder.layer.23.norm2.weight": "model-00003-of-00003.safetensors",
"encoder.layer.24.attention.attention.key.bias": "model-00003-of-00003.safetensors",
"encoder.layer.24.attention.attention.key.weight": "model-00003-of-00003.safetensors",
"encoder.layer.24.attention.attention.query.bias": "model-00003-of-00003.safetensors",
"encoder.layer.24.attention.attention.query.weight": "model-00003-of-00003.safetensors",
"encoder.layer.24.attention.attention.value.bias": "model-00003-of-00003.safetensors",
"encoder.layer.24.attention.attention.value.weight": "model-00003-of-00003.safetensors",
"encoder.layer.24.attention.output.dense.bias": "model-00003-of-00003.safetensors",
"encoder.layer.24.attention.output.dense.weight": "model-00003-of-00003.safetensors",
"encoder.layer.24.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
"encoder.layer.24.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
"encoder.layer.24.mlp.weights_in.bias": "model-00003-of-00003.safetensors",
"encoder.layer.24.mlp.weights_in.weight": "model-00003-of-00003.safetensors",
"encoder.layer.24.mlp.weights_out.bias": "model-00003-of-00003.safetensors",
"encoder.layer.24.mlp.weights_out.weight": "model-00003-of-00003.safetensors",
"encoder.layer.24.norm1.bias": "model-00003-of-00003.safetensors",
"encoder.layer.24.norm1.weight": "model-00003-of-00003.safetensors",
"encoder.layer.24.norm2.bias": "model-00003-of-00003.safetensors",
"encoder.layer.24.norm2.weight": "model-00003-of-00003.safetensors",
"encoder.layer.25.attention.attention.key.bias": "model-00003-of-00003.safetensors",
"encoder.layer.25.attention.attention.key.weight": "model-00003-of-00003.safetensors",
"encoder.layer.25.attention.attention.query.bias": "model-00003-of-00003.safetensors",
"encoder.layer.25.attention.attention.query.weight": "model-00003-of-00003.safetensors",
"encoder.layer.25.attention.attention.value.bias": "model-00003-of-00003.safetensors",
"encoder.layer.25.attention.attention.value.weight": "model-00003-of-00003.safetensors",
"encoder.layer.25.attention.output.dense.bias": "model-00003-of-00003.safetensors",
"encoder.layer.25.attention.output.dense.weight": "model-00003-of-00003.safetensors",
"encoder.layer.25.layer_scale1.lambda1": "model-00003-of-00003.safetensors",
"encoder.layer.25.layer_scale2.lambda1": "model-00003-of-00003.safetensors",
"encoder.layer.25.mlp.weights_in.bias": "model-00003-of-00003.safetensors",
"encoder.layer.25.mlp.weights_in.weight": "model-00003-of-00003.safetensors",
"encoder.layer.25.mlp.weights_out.bias": "model-00003-of-00003.safetensors",
"encoder.layer.25.mlp.weights_out.weight": "model-00003-of-00003.safetensors",
"encoder.layer.25.norm1.bias": "model-00003-of-00003.safetensors",
"encoder.layer.25.norm1.weight": "model-00003-of-00003.safetensors",
"encoder.layer.25.norm2.bias": "model-00003-of-00003.safetensors",
"encoder.layer.25.norm2.weight": "model-00003-of-00003.safetensors",
"encoder.layer.3.attention.attention.key.bias": "model-00001-of-00003.safetensors",
"encoder.layer.3.attention.attention.key.weight": "model-00001-of-00003.safetensors",
"encoder.layer.3.attention.attention.query.bias": "model-00001-of-00003.safetensors",
"encoder.layer.3.attention.attention.query.weight": "model-00001-of-00003.safetensors",
"encoder.layer.3.attention.attention.value.bias": "model-00001-of-00003.safetensors",
"encoder.layer.3.attention.attention.value.weight": "model-00001-of-00003.safetensors",
"encoder.layer.3.attention.output.dense.bias": "model-00001-of-00003.safetensors",
"encoder.layer.3.attention.output.dense.weight": "model-00001-of-00003.safetensors",
"encoder.layer.3.layer_scale1.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.3.layer_scale2.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.3.mlp.weights_in.bias": "model-00001-of-00003.safetensors",
"encoder.layer.3.mlp.weights_in.weight": "model-00001-of-00003.safetensors",
"encoder.layer.3.mlp.weights_out.bias": "model-00001-of-00003.safetensors",
"encoder.layer.3.mlp.weights_out.weight": "model-00001-of-00003.safetensors",
"encoder.layer.3.norm1.bias": "model-00001-of-00003.safetensors",
"encoder.layer.3.norm1.weight": "model-00001-of-00003.safetensors",
"encoder.layer.3.norm2.bias": "model-00001-of-00003.safetensors",
"encoder.layer.3.norm2.weight": "model-00001-of-00003.safetensors",
"encoder.layer.4.attention.attention.key.bias": "model-00001-of-00003.safetensors",
"encoder.layer.4.attention.attention.key.weight": "model-00001-of-00003.safetensors",
"encoder.layer.4.attention.attention.query.bias": "model-00001-of-00003.safetensors",
"encoder.layer.4.attention.attention.query.weight": "model-00001-of-00003.safetensors",
"encoder.layer.4.attention.attention.value.bias": "model-00001-of-00003.safetensors",
"encoder.layer.4.attention.attention.value.weight": "model-00001-of-00003.safetensors",
"encoder.layer.4.attention.output.dense.bias": "model-00001-of-00003.safetensors",
"encoder.layer.4.attention.output.dense.weight": "model-00001-of-00003.safetensors",
"encoder.layer.4.layer_scale1.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.4.layer_scale2.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.4.mlp.weights_in.bias": "model-00001-of-00003.safetensors",
"encoder.layer.4.mlp.weights_in.weight": "model-00001-of-00003.safetensors",
"encoder.layer.4.mlp.weights_out.bias": "model-00001-of-00003.safetensors",
"encoder.layer.4.mlp.weights_out.weight": "model-00001-of-00003.safetensors",
"encoder.layer.4.norm1.bias": "model-00001-of-00003.safetensors",
"encoder.layer.4.norm1.weight": "model-00001-of-00003.safetensors",
"encoder.layer.4.norm2.bias": "model-00001-of-00003.safetensors",
"encoder.layer.4.norm2.weight": "model-00001-of-00003.safetensors",
"encoder.layer.5.attention.attention.key.bias": "model-00001-of-00003.safetensors",
"encoder.layer.5.attention.attention.key.weight": "model-00001-of-00003.safetensors",
"encoder.layer.5.attention.attention.query.bias": "model-00001-of-00003.safetensors",
"encoder.layer.5.attention.attention.query.weight": "model-00001-of-00003.safetensors",
"encoder.layer.5.attention.attention.value.bias": "model-00001-of-00003.safetensors",
"encoder.layer.5.attention.attention.value.weight": "model-00001-of-00003.safetensors",
"encoder.layer.5.attention.output.dense.bias": "model-00001-of-00003.safetensors",
"encoder.layer.5.attention.output.dense.weight": "model-00001-of-00003.safetensors",
"encoder.layer.5.layer_scale1.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.5.layer_scale2.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.5.mlp.weights_in.bias": "model-00001-of-00003.safetensors",
"encoder.layer.5.mlp.weights_in.weight": "model-00001-of-00003.safetensors",
"encoder.layer.5.mlp.weights_out.bias": "model-00001-of-00003.safetensors",
"encoder.layer.5.mlp.weights_out.weight": "model-00001-of-00003.safetensors",
"encoder.layer.5.norm1.bias": "model-00001-of-00003.safetensors",
"encoder.layer.5.norm1.weight": "model-00001-of-00003.safetensors",
"encoder.layer.5.norm2.bias": "model-00001-of-00003.safetensors",
"encoder.layer.5.norm2.weight": "model-00001-of-00003.safetensors",
"encoder.layer.6.attention.attention.key.bias": "model-00001-of-00003.safetensors",
"encoder.layer.6.attention.attention.key.weight": "model-00001-of-00003.safetensors",
"encoder.layer.6.attention.attention.query.bias": "model-00001-of-00003.safetensors",
"encoder.layer.6.attention.attention.query.weight": "model-00001-of-00003.safetensors",
"encoder.layer.6.attention.attention.value.bias": "model-00001-of-00003.safetensors",
"encoder.layer.6.attention.attention.value.weight": "model-00001-of-00003.safetensors",
"encoder.layer.6.attention.output.dense.bias": "model-00001-of-00003.safetensors",
"encoder.layer.6.attention.output.dense.weight": "model-00001-of-00003.safetensors",
"encoder.layer.6.layer_scale1.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.6.layer_scale2.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.6.mlp.weights_in.bias": "model-00001-of-00003.safetensors",
"encoder.layer.6.mlp.weights_in.weight": "model-00001-of-00003.safetensors",
"encoder.layer.6.mlp.weights_out.bias": "model-00001-of-00003.safetensors",
"encoder.layer.6.mlp.weights_out.weight": "model-00001-of-00003.safetensors",
"encoder.layer.6.norm1.bias": "model-00001-of-00003.safetensors",
"encoder.layer.6.norm1.weight": "model-00001-of-00003.safetensors",
"encoder.layer.6.norm2.bias": "model-00001-of-00003.safetensors",
"encoder.layer.6.norm2.weight": "model-00001-of-00003.safetensors",
"encoder.layer.7.attention.attention.key.bias": "model-00001-of-00003.safetensors",
"encoder.layer.7.attention.attention.key.weight": "model-00001-of-00003.safetensors",
"encoder.layer.7.attention.attention.query.bias": "model-00001-of-00003.safetensors",
"encoder.layer.7.attention.attention.query.weight": "model-00001-of-00003.safetensors",
"encoder.layer.7.attention.attention.value.bias": "model-00001-of-00003.safetensors",
"encoder.layer.7.attention.attention.value.weight": "model-00001-of-00003.safetensors",
"encoder.layer.7.attention.output.dense.bias": "model-00001-of-00003.safetensors",
"encoder.layer.7.attention.output.dense.weight": "model-00001-of-00003.safetensors",
"encoder.layer.7.layer_scale1.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.7.layer_scale2.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.7.mlp.weights_in.bias": "model-00001-of-00003.safetensors",
"encoder.layer.7.mlp.weights_in.weight": "model-00001-of-00003.safetensors",
"encoder.layer.7.mlp.weights_out.bias": "model-00001-of-00003.safetensors",
"encoder.layer.7.mlp.weights_out.weight": "model-00001-of-00003.safetensors",
"encoder.layer.7.norm1.bias": "model-00001-of-00003.safetensors",
"encoder.layer.7.norm1.weight": "model-00001-of-00003.safetensors",
"encoder.layer.7.norm2.bias": "model-00001-of-00003.safetensors",
"encoder.layer.7.norm2.weight": "model-00001-of-00003.safetensors",
"encoder.layer.8.attention.attention.key.bias": "model-00001-of-00003.safetensors",
"encoder.layer.8.attention.attention.key.weight": "model-00001-of-00003.safetensors",
"encoder.layer.8.attention.attention.query.bias": "model-00001-of-00003.safetensors",
"encoder.layer.8.attention.attention.query.weight": "model-00001-of-00003.safetensors",
"encoder.layer.8.attention.attention.value.bias": "model-00001-of-00003.safetensors",
"encoder.layer.8.attention.attention.value.weight": "model-00001-of-00003.safetensors",
"encoder.layer.8.attention.output.dense.bias": "model-00001-of-00003.safetensors",
"encoder.layer.8.attention.output.dense.weight": "model-00001-of-00003.safetensors",
"encoder.layer.8.layer_scale1.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.8.layer_scale2.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.8.mlp.weights_in.bias": "model-00001-of-00003.safetensors",
"encoder.layer.8.mlp.weights_in.weight": "model-00001-of-00003.safetensors",
"encoder.layer.8.mlp.weights_out.bias": "model-00001-of-00003.safetensors",
"encoder.layer.8.mlp.weights_out.weight": "model-00001-of-00003.safetensors",
"encoder.layer.8.norm1.bias": "model-00001-of-00003.safetensors",
"encoder.layer.8.norm1.weight": "model-00001-of-00003.safetensors",
"encoder.layer.8.norm2.bias": "model-00001-of-00003.safetensors",
"encoder.layer.8.norm2.weight": "model-00001-of-00003.safetensors",
"encoder.layer.9.attention.attention.key.bias": "model-00001-of-00003.safetensors",
"encoder.layer.9.attention.attention.key.weight": "model-00001-of-00003.safetensors",
"encoder.layer.9.attention.attention.query.bias": "model-00001-of-00003.safetensors",
"encoder.layer.9.attention.attention.query.weight": "model-00001-of-00003.safetensors",
"encoder.layer.9.attention.attention.value.bias": "model-00001-of-00003.safetensors",
"encoder.layer.9.attention.attention.value.weight": "model-00001-of-00003.safetensors",
"encoder.layer.9.attention.output.dense.bias": "model-00001-of-00003.safetensors",
"encoder.layer.9.attention.output.dense.weight": "model-00001-of-00003.safetensors",
"encoder.layer.9.layer_scale1.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.9.layer_scale2.lambda1": "model-00001-of-00003.safetensors",
"encoder.layer.9.mlp.weights_in.bias": "model-00001-of-00003.safetensors",
"encoder.layer.9.mlp.weights_in.weight": "model-00001-of-00003.safetensors",
"encoder.layer.9.mlp.weights_out.bias": "model-00001-of-00003.safetensors",
"encoder.layer.9.mlp.weights_out.weight": "model-00001-of-00003.safetensors",
"encoder.layer.9.norm1.bias": "model-00001-of-00003.safetensors",
"encoder.layer.9.norm1.weight": "model-00001-of-00003.safetensors",
"encoder.layer.9.norm2.bias": "model-00001-of-00003.safetensors",
"encoder.layer.9.norm2.weight": "model-00001-of-00003.safetensors",
"layernorm.bias": "model-00003-of-00003.safetensors",
"layernorm.weight": "model-00003-of-00003.safetensors"
}
}
|