File size: 37,820 Bytes
0494871 |
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 |
{
"metadata": {
"total_size": 5904482288
},
"weight_map": {
"cls.predictions.bias": "pytorch_model-00006-of-00006.bin",
"cls.predictions.decoder.bias": "pytorch_model-00006-of-00006.bin",
"cls.predictions.decoder.weight": "pytorch_model-00006-of-00006.bin",
"cls.predictions.transform.LayerNorm.bias": "pytorch_model-00006-of-00006.bin",
"cls.predictions.transform.LayerNorm.weight": "pytorch_model-00006-of-00006.bin",
"cls.predictions.transform.dense.bias": "pytorch_model-00006-of-00006.bin",
"cls.predictions.transform.dense.weight": "pytorch_model-00006-of-00006.bin",
"deberta.embeddings.LayerNorm.bias": "pytorch_model-00001-of-00006.bin",
"deberta.embeddings.LayerNorm.weight": "pytorch_model-00001-of-00006.bin",
"deberta.embeddings.position_ids": "pytorch_model-00001-of-00006.bin",
"deberta.embeddings.word_embeddings.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.LayerNorm.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.LayerNorm.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.0.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.attention.output.dense.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.attention.output.dense.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.attention.self.key_proj.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.attention.self.key_proj.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.attention.self.query_proj.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.attention.self.query_proj.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.attention.self.value_proj.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.attention.self.value_proj.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.intermediate.dense.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.intermediate.dense.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.output.LayerNorm.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.output.LayerNorm.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.output.dense.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.0.output.dense.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.attention.output.dense.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.attention.output.dense.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.attention.self.key_proj.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.attention.self.key_proj.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.attention.self.query_proj.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.attention.self.query_proj.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.attention.self.value_proj.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.attention.self.value_proj.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.intermediate.dense.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.intermediate.dense.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.output.LayerNorm.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.output.LayerNorm.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.output.dense.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.1.output.dense.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.10.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.attention.self.key_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.attention.self.key_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.attention.self.query_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.attention.self.query_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.attention.self.value_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.attention.self.value_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.intermediate.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.intermediate.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.output.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.10.output.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.attention.self.key_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.attention.self.key_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.attention.self.query_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.attention.self.query_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.attention.self.value_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.attention.self.value_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.intermediate.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.intermediate.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.output.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.11.output.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.12.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.12.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.12.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.12.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.12.attention.self.key_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.12.attention.self.key_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.12.attention.self.query_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.12.attention.self.query_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.12.attention.self.value_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.12.attention.self.value_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.12.intermediate.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.12.intermediate.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.12.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.12.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.12.output.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.12.output.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.attention.self.key_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.attention.self.key_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.attention.self.query_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.attention.self.query_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.attention.self.value_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.attention.self.value_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.intermediate.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.intermediate.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.output.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.13.output.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.attention.self.key_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.attention.self.key_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.attention.self.query_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.attention.self.query_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.attention.self.value_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.attention.self.value_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.intermediate.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.intermediate.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.output.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.14.output.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.attention.self.key_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.attention.self.key_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.attention.self.query_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.attention.self.query_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.attention.self.value_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.attention.self.value_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.intermediate.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.intermediate.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.output.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.15.output.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.attention.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.attention.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.attention.output.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.attention.output.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.attention.self.key_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.attention.self.key_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.attention.self.query_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.attention.self.query_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.attention.self.value_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.attention.self.value_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.intermediate.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.intermediate.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.output.LayerNorm.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.output.LayerNorm.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.output.dense.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.16.output.dense.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.17.attention.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.17.attention.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.17.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.17.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.17.attention.self.key_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.17.attention.self.key_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.17.attention.self.query_proj.bias": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.17.attention.self.query_proj.weight": "pytorch_model-00004-of-00006.bin",
"deberta.encoder.layer.17.attention.self.value_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.17.attention.self.value_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.17.intermediate.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.17.intermediate.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.17.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.17.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.17.output.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.17.output.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.attention.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.attention.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.attention.self.key_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.attention.self.key_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.attention.self.query_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.attention.self.query_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.attention.self.value_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.attention.self.value_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.intermediate.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.intermediate.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.output.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.18.output.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.attention.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.attention.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.attention.self.key_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.attention.self.key_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.attention.self.query_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.attention.self.query_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.attention.self.value_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.attention.self.value_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.intermediate.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.intermediate.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.output.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.19.output.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.2.attention.output.LayerNorm.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.2.attention.output.LayerNorm.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.2.attention.output.dense.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.2.attention.output.dense.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.2.attention.self.key_proj.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.2.attention.self.key_proj.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.2.attention.self.query_proj.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.2.attention.self.query_proj.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.2.attention.self.value_proj.bias": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.2.attention.self.value_proj.weight": "pytorch_model-00001-of-00006.bin",
"deberta.encoder.layer.2.intermediate.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.2.intermediate.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.2.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.2.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.2.output.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.2.output.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.20.attention.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.attention.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.attention.self.key_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.attention.self.key_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.attention.self.query_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.attention.self.query_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.attention.self.value_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.attention.self.value_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.intermediate.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.intermediate.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.output.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.20.output.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.attention.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.attention.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.attention.output.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.attention.output.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.attention.self.key_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.attention.self.key_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.attention.self.query_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.attention.self.query_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.attention.self.value_proj.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.attention.self.value_proj.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.intermediate.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.intermediate.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.output.LayerNorm.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.output.LayerNorm.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.output.dense.bias": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.21.output.dense.weight": "pytorch_model-00005-of-00006.bin",
"deberta.encoder.layer.22.attention.output.LayerNorm.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.attention.output.LayerNorm.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.attention.output.dense.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.attention.output.dense.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.attention.self.key_proj.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.attention.self.key_proj.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.attention.self.query_proj.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.attention.self.query_proj.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.attention.self.value_proj.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.attention.self.value_proj.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.intermediate.dense.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.intermediate.dense.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.output.LayerNorm.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.output.LayerNorm.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.output.dense.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.22.output.dense.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.attention.output.LayerNorm.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.attention.output.LayerNorm.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.attention.output.dense.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.attention.output.dense.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.attention.self.key_proj.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.attention.self.key_proj.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.attention.self.query_proj.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.attention.self.query_proj.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.attention.self.value_proj.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.attention.self.value_proj.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.intermediate.dense.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.intermediate.dense.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.output.LayerNorm.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.output.LayerNorm.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.output.dense.bias": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.23.output.dense.weight": "pytorch_model-00006-of-00006.bin",
"deberta.encoder.layer.3.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.attention.output.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.attention.output.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.attention.self.key_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.attention.self.key_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.attention.self.query_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.attention.self.query_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.attention.self.value_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.attention.self.value_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.intermediate.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.intermediate.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.output.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.3.output.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.attention.output.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.attention.output.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.attention.self.key_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.attention.self.key_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.attention.self.query_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.attention.self.query_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.attention.self.value_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.attention.self.value_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.intermediate.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.intermediate.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.output.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.4.output.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.attention.output.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.attention.output.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.attention.self.key_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.attention.self.key_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.attention.self.query_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.attention.self.query_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.attention.self.value_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.attention.self.value_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.intermediate.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.intermediate.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.output.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.5.output.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.attention.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.attention.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.attention.output.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.attention.output.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.attention.self.key_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.attention.self.key_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.attention.self.query_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.attention.self.query_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.attention.self.value_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.attention.self.value_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.intermediate.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.intermediate.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.output.LayerNorm.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.output.LayerNorm.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.output.dense.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.6.output.dense.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.7.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.7.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.7.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.7.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.7.attention.self.key_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.7.attention.self.key_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.7.attention.self.query_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.7.attention.self.query_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.7.attention.self.value_proj.bias": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.7.attention.self.value_proj.weight": "pytorch_model-00002-of-00006.bin",
"deberta.encoder.layer.7.intermediate.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.7.intermediate.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.7.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.7.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.7.output.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.7.output.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.attention.self.key_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.attention.self.key_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.attention.self.query_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.attention.self.query_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.attention.self.value_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.attention.self.value_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.intermediate.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.intermediate.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.output.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.8.output.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.attention.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.attention.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.attention.output.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.attention.output.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.attention.self.key_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.attention.self.key_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.attention.self.query_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.attention.self.query_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.attention.self.value_proj.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.attention.self.value_proj.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.intermediate.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.intermediate.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.output.LayerNorm.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.output.LayerNorm.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.output.dense.bias": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.layer.9.output.dense.weight": "pytorch_model-00003-of-00006.bin",
"deberta.encoder.rel_embeddings.weight": "pytorch_model-00006-of-00006.bin"
}
}
|