File size: 41,662 Bytes
6d3aab1 |
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 |
{
"metadata": {
"total_size": 38069813248
},
"weight_map": {
"encoder.layers.0.ffn.ffn.w_in.w_0.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.0.ffn.ffn.w_in.w_1.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.0.ffn.ffn.w_out.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.0.ffn.layernorm_before_ffn.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.0.self_att.layernorm_before_attention.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.0.self_att.self_attention.attention_out.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.0.self_att.self_attention.project_k.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.0.self_att.self_attention.project_q.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.0.self_att.self_attention.project_v.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.1.ffn.ffn.w_in.w_0.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.1.ffn.ffn.w_in.w_1.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.1.ffn.ffn.w_out.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.1.ffn.layernorm_before_ffn.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.1.self_att.layernorm_before_attention.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.1.self_att.self_attention.attention_out.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.1.self_att.self_attention.project_k.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.1.self_att.self_attention.project_q.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.1.self_att.self_attention.project_v.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.10.ffn.ffn.w_in.w_0.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.10.ffn.ffn.w_in.w_1.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.10.ffn.ffn.w_out.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.10.ffn.layernorm_before_ffn.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.10.self_att.layernorm_before_attention.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.10.self_att.self_attention.attention_out.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.10.self_att.self_attention.project_k.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.10.self_att.self_attention.project_q.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.10.self_att.self_attention.project_v.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.11.ffn.ffn.w_in.w_0.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.11.ffn.ffn.w_in.w_1.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.11.ffn.ffn.w_out.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.11.ffn.layernorm_before_ffn.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.11.self_att.layernorm_before_attention.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.11.self_att.self_attention.attention_out.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.11.self_att.self_attention.project_k.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.11.self_att.self_attention.project_q.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.11.self_att.self_attention.project_v.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.12.ffn.ffn.w_in.w_0.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.12.ffn.ffn.w_in.w_1.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.12.ffn.ffn.w_out.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.12.ffn.layernorm_before_ffn.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.12.self_att.layernorm_before_attention.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.12.self_att.self_attention.attention_out.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.12.self_att.self_attention.project_k.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.12.self_att.self_attention.project_q.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.12.self_att.self_attention.project_v.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.13.ffn.ffn.w_in.w_0.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.13.ffn.ffn.w_in.w_1.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.13.ffn.ffn.w_out.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.13.ffn.layernorm_before_ffn.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.13.self_att.layernorm_before_attention.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.13.self_att.self_attention.attention_out.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.13.self_att.self_attention.project_k.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.13.self_att.self_attention.project_q.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.13.self_att.self_attention.project_v.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.14.ffn.ffn.w_in.w_0.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.14.ffn.ffn.w_in.w_1.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.14.ffn.ffn.w_out.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.14.ffn.layernorm_before_ffn.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.14.self_att.layernorm_before_attention.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.14.self_att.self_attention.attention_out.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.14.self_att.self_attention.project_k.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.14.self_att.self_attention.project_q.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.14.self_att.self_attention.project_v.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.15.ffn.ffn.w_in.w_0.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.15.ffn.ffn.w_in.w_1.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.15.ffn.ffn.w_out.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.15.ffn.layernorm_before_ffn.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.15.self_att.layernorm_before_attention.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.15.self_att.self_attention.attention_out.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.15.self_att.self_attention.project_k.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.15.self_att.self_attention.project_q.weight": "pytorch_model-00004-of-00013.bin",
"encoder.layers.15.self_att.self_attention.project_v.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.16.ffn.ffn.w_in.w_0.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.16.ffn.ffn.w_in.w_1.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.16.ffn.ffn.w_out.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.16.ffn.layernorm_before_ffn.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.16.self_att.layernorm_before_attention.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.16.self_att.self_attention.attention_out.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.16.self_att.self_attention.project_k.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.16.self_att.self_attention.project_q.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.16.self_att.self_attention.project_v.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.17.ffn.ffn.w_in.w_0.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.17.ffn.ffn.w_in.w_1.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.17.ffn.ffn.w_out.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.17.ffn.layernorm_before_ffn.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.17.self_att.layernorm_before_attention.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.17.self_att.self_attention.attention_out.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.17.self_att.self_attention.project_k.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.17.self_att.self_attention.project_q.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.17.self_att.self_attention.project_v.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.18.ffn.ffn.w_in.w_0.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.18.ffn.ffn.w_in.w_1.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.18.ffn.ffn.w_out.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.18.ffn.layernorm_before_ffn.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.18.self_att.layernorm_before_attention.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.18.self_att.self_attention.attention_out.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.18.self_att.self_attention.project_k.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.18.self_att.self_attention.project_q.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.18.self_att.self_attention.project_v.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.19.ffn.ffn.w_in.w_0.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.19.ffn.ffn.w_in.w_1.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.19.ffn.ffn.w_out.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.19.ffn.layernorm_before_ffn.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.19.self_att.layernorm_before_attention.weight": "pytorch_model-00005-of-00013.bin",
"encoder.layers.19.self_att.self_attention.attention_out.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.19.self_att.self_attention.project_k.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.19.self_att.self_attention.project_q.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.19.self_att.self_attention.project_v.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.2.ffn.ffn.w_in.w_0.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.2.ffn.ffn.w_in.w_1.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.2.ffn.ffn.w_out.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.2.ffn.layernorm_before_ffn.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.2.self_att.layernorm_before_attention.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.2.self_att.self_attention.attention_out.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.2.self_att.self_attention.project_k.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.2.self_att.self_attention.project_q.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.2.self_att.self_attention.project_v.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.20.ffn.ffn.w_in.w_0.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.20.ffn.ffn.w_in.w_1.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.20.ffn.ffn.w_out.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.20.ffn.layernorm_before_ffn.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.20.self_att.layernorm_before_attention.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.20.self_att.self_attention.attention_out.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.20.self_att.self_attention.project_k.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.20.self_att.self_attention.project_q.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.20.self_att.self_attention.project_v.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.21.ffn.ffn.w_in.w_0.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.21.ffn.ffn.w_in.w_1.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.21.ffn.ffn.w_out.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.21.ffn.layernorm_before_ffn.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.21.self_att.layernorm_before_attention.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.21.self_att.self_attention.attention_out.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.21.self_att.self_attention.project_k.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.21.self_att.self_attention.project_q.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.21.self_att.self_attention.project_v.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.22.ffn.ffn.w_in.w_0.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.22.ffn.ffn.w_in.w_1.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.22.ffn.ffn.w_out.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.22.ffn.layernorm_before_ffn.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.22.self_att.layernorm_before_attention.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.22.self_att.self_attention.attention_out.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.22.self_att.self_attention.project_k.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.22.self_att.self_attention.project_q.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.22.self_att.self_attention.project_v.weight": "pytorch_model-00006-of-00013.bin",
"encoder.layers.23.ffn.ffn.w_in.w_0.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.23.ffn.ffn.w_in.w_1.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.23.ffn.ffn.w_out.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.23.ffn.layernorm_before_ffn.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.23.self_att.layernorm_before_attention.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.23.self_att.self_attention.attention_out.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.23.self_att.self_attention.project_k.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.23.self_att.self_attention.project_q.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.23.self_att.self_attention.project_v.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.24.ffn.ffn.w_in.w_0.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.24.ffn.ffn.w_in.w_1.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.24.ffn.ffn.w_out.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.24.ffn.layernorm_before_ffn.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.24.self_att.layernorm_before_attention.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.24.self_att.self_attention.attention_out.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.24.self_att.self_attention.project_k.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.24.self_att.self_attention.project_q.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.24.self_att.self_attention.project_v.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.25.ffn.ffn.w_in.w_0.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.25.ffn.ffn.w_in.w_1.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.25.ffn.ffn.w_out.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.25.ffn.layernorm_before_ffn.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.25.self_att.layernorm_before_attention.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.25.self_att.self_attention.attention_out.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.25.self_att.self_attention.project_k.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.25.self_att.self_attention.project_q.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.25.self_att.self_attention.project_v.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.26.ffn.ffn.w_in.w_0.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.26.ffn.ffn.w_in.w_1.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.26.ffn.ffn.w_out.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.26.ffn.layernorm_before_ffn.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.26.self_att.layernorm_before_attention.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.26.self_att.self_attention.attention_out.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.26.self_att.self_attention.project_k.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.26.self_att.self_attention.project_q.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.26.self_att.self_attention.project_v.weight": "pytorch_model-00007-of-00013.bin",
"encoder.layers.27.ffn.ffn.w_in.w_0.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.27.ffn.ffn.w_in.w_1.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.27.ffn.ffn.w_out.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.27.ffn.layernorm_before_ffn.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.27.self_att.layernorm_before_attention.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.27.self_att.self_attention.attention_out.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.27.self_att.self_attention.project_k.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.27.self_att.self_attention.project_q.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.27.self_att.self_attention.project_v.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.28.ffn.ffn.w_in.w_0.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.28.ffn.ffn.w_in.w_1.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.28.ffn.ffn.w_out.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.28.ffn.layernorm_before_ffn.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.28.self_att.layernorm_before_attention.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.28.self_att.self_attention.attention_out.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.28.self_att.self_attention.project_k.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.28.self_att.self_attention.project_q.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.28.self_att.self_attention.project_v.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.29.ffn.ffn.w_in.w_0.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.29.ffn.ffn.w_in.w_1.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.29.ffn.ffn.w_out.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.29.ffn.layernorm_before_ffn.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.29.self_att.layernorm_before_attention.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.29.self_att.self_attention.attention_out.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.29.self_att.self_attention.project_k.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.29.self_att.self_attention.project_q.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.29.self_att.self_attention.project_v.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.3.ffn.ffn.w_in.w_0.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.3.ffn.ffn.w_in.w_1.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.3.ffn.ffn.w_out.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.3.ffn.layernorm_before_ffn.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.3.self_att.layernorm_before_attention.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.3.self_att.self_attention.attention_out.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.3.self_att.self_attention.project_k.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.3.self_att.self_attention.project_q.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.3.self_att.self_attention.project_v.weight": "pytorch_model-00001-of-00013.bin",
"encoder.layers.30.ffn.ffn.w_in.w_0.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.30.ffn.ffn.w_in.w_1.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.30.ffn.ffn.w_out.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.30.ffn.layernorm_before_ffn.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.30.self_att.layernorm_before_attention.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.30.self_att.self_attention.attention_out.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.30.self_att.self_attention.project_k.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.30.self_att.self_attention.project_q.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.30.self_att.self_attention.project_v.weight": "pytorch_model-00008-of-00013.bin",
"encoder.layers.31.ffn.ffn.w_in.w_0.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.31.ffn.ffn.w_in.w_1.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.31.ffn.ffn.w_out.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.31.ffn.layernorm_before_ffn.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.31.self_att.layernorm_before_attention.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.31.self_att.self_attention.attention_out.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.31.self_att.self_attention.project_k.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.31.self_att.self_attention.project_q.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.31.self_att.self_attention.project_v.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.32.ffn.ffn.w_in.w_0.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.32.ffn.ffn.w_in.w_1.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.32.ffn.ffn.w_out.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.32.ffn.layernorm_before_ffn.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.32.self_att.layernorm_before_attention.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.32.self_att.self_attention.attention_out.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.32.self_att.self_attention.project_k.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.32.self_att.self_attention.project_q.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.32.self_att.self_attention.project_v.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.33.ffn.ffn.w_in.w_0.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.33.ffn.ffn.w_in.w_1.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.33.ffn.ffn.w_out.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.33.ffn.layernorm_before_ffn.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.33.self_att.layernorm_before_attention.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.33.self_att.self_attention.attention_out.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.33.self_att.self_attention.project_k.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.33.self_att.self_attention.project_q.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.33.self_att.self_attention.project_v.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.34.ffn.ffn.w_in.w_0.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.34.ffn.ffn.w_in.w_1.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.34.ffn.ffn.w_out.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.34.ffn.layernorm_before_ffn.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.34.self_att.layernorm_before_attention.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.34.self_att.self_attention.attention_out.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.34.self_att.self_attention.project_k.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.34.self_att.self_attention.project_q.weight": "pytorch_model-00009-of-00013.bin",
"encoder.layers.34.self_att.self_attention.project_v.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.35.ffn.ffn.w_in.w_0.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.35.ffn.ffn.w_in.w_1.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.35.ffn.ffn.w_out.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.35.ffn.layernorm_before_ffn.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.35.self_att.layernorm_before_attention.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.35.self_att.self_attention.attention_out.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.35.self_att.self_attention.project_k.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.35.self_att.self_attention.project_q.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.35.self_att.self_attention.project_v.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.36.ffn.ffn.w_in.w_0.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.36.ffn.ffn.w_in.w_1.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.36.ffn.ffn.w_out.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.36.ffn.layernorm_before_ffn.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.36.self_att.layernorm_before_attention.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.36.self_att.self_attention.attention_out.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.36.self_att.self_attention.project_k.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.36.self_att.self_attention.project_q.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.36.self_att.self_attention.project_v.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.37.ffn.ffn.w_in.w_0.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.37.ffn.ffn.w_in.w_1.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.37.ffn.ffn.w_out.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.37.ffn.layernorm_before_ffn.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.37.self_att.layernorm_before_attention.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.37.self_att.self_attention.attention_out.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.37.self_att.self_attention.project_k.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.37.self_att.self_attention.project_q.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.37.self_att.self_attention.project_v.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.38.ffn.ffn.w_in.w_0.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.38.ffn.ffn.w_in.w_1.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.38.ffn.ffn.w_out.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.38.ffn.layernorm_before_ffn.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.38.self_att.layernorm_before_attention.weight": "pytorch_model-00010-of-00013.bin",
"encoder.layers.38.self_att.self_attention.attention_out.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.38.self_att.self_attention.project_k.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.38.self_att.self_attention.project_q.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.38.self_att.self_attention.project_v.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.39.ffn.ffn.w_in.w_0.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.39.ffn.ffn.w_in.w_1.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.39.ffn.ffn.w_out.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.39.ffn.layernorm_before_ffn.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.39.self_att.layernorm_before_attention.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.39.self_att.self_attention.attention_out.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.39.self_att.self_attention.project_k.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.39.self_att.self_attention.project_q.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.39.self_att.self_attention.project_v.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.4.ffn.ffn.w_in.w_0.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.4.ffn.ffn.w_in.w_1.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.4.ffn.ffn.w_out.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.4.ffn.layernorm_before_ffn.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.4.self_att.layernorm_before_attention.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.4.self_att.self_attention.attention_out.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.4.self_att.self_attention.project_k.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.4.self_att.self_attention.project_q.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.4.self_att.self_attention.project_v.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.40.ffn.ffn.w_in.w_0.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.40.ffn.ffn.w_in.w_1.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.40.ffn.ffn.w_out.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.40.ffn.layernorm_before_ffn.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.40.self_att.layernorm_before_attention.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.40.self_att.self_attention.attention_out.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.40.self_att.self_attention.project_k.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.40.self_att.self_attention.project_q.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.40.self_att.self_attention.project_v.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.41.ffn.ffn.w_in.w_0.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.41.ffn.ffn.w_in.w_1.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.41.ffn.ffn.w_out.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.41.ffn.layernorm_before_ffn.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.41.self_att.layernorm_before_attention.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.41.self_att.self_attention.attention_out.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.41.self_att.self_attention.project_k.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.41.self_att.self_attention.project_q.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.41.self_att.self_attention.project_v.weight": "pytorch_model-00011-of-00013.bin",
"encoder.layers.42.ffn.ffn.w_in.w_0.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.42.ffn.ffn.w_in.w_1.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.42.ffn.ffn.w_out.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.42.ffn.layernorm_before_ffn.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.42.self_att.layernorm_before_attention.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.42.self_att.self_attention.attention_out.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.42.self_att.self_attention.project_k.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.42.self_att.self_attention.project_q.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.42.self_att.self_attention.project_v.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.43.ffn.ffn.w_in.w_0.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.43.ffn.ffn.w_in.w_1.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.43.ffn.ffn.w_out.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.43.ffn.layernorm_before_ffn.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.43.self_att.layernorm_before_attention.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.43.self_att.self_attention.attention_out.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.43.self_att.self_attention.project_k.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.43.self_att.self_attention.project_q.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.43.self_att.self_attention.project_v.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.44.ffn.ffn.w_in.w_0.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.44.ffn.ffn.w_in.w_1.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.44.ffn.ffn.w_out.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.44.ffn.layernorm_before_ffn.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.44.self_att.layernorm_before_attention.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.44.self_att.self_attention.attention_out.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.44.self_att.self_attention.project_k.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.44.self_att.self_attention.project_q.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.44.self_att.self_attention.project_v.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.45.ffn.ffn.w_in.w_0.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.45.ffn.ffn.w_in.w_1.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.45.ffn.ffn.w_out.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.45.ffn.layernorm_before_ffn.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.45.self_att.layernorm_before_attention.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.45.self_att.self_attention.attention_out.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.45.self_att.self_attention.project_k.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.45.self_att.self_attention.project_q.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.45.self_att.self_attention.project_v.weight": "pytorch_model-00012-of-00013.bin",
"encoder.layers.46.ffn.ffn.w_in.w_0.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.46.ffn.ffn.w_in.w_1.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.46.ffn.ffn.w_out.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.46.ffn.layernorm_before_ffn.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.46.self_att.layernorm_before_attention.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.46.self_att.self_attention.attention_out.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.46.self_att.self_attention.project_k.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.46.self_att.self_attention.project_q.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.46.self_att.self_attention.project_v.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.47.ffn.ffn.w_in.w_0.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.47.ffn.ffn.w_in.w_1.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.47.ffn.ffn.w_out.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.47.ffn.layernorm_before_ffn.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.47.self_att.layernorm_before_attention.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.47.self_att.self_attention.attention_out.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.47.self_att.self_attention.project_k.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.47.self_att.self_attention.project_q.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.47.self_att.self_attention.project_v.weight": "pytorch_model-00013-of-00013.bin",
"encoder.layers.5.ffn.ffn.w_in.w_0.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.5.ffn.ffn.w_in.w_1.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.5.ffn.ffn.w_out.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.5.ffn.layernorm_before_ffn.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.5.self_att.layernorm_before_attention.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.5.self_att.self_attention.attention_out.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.5.self_att.self_attention.project_k.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.5.self_att.self_attention.project_q.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.5.self_att.self_attention.project_v.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.6.ffn.ffn.w_in.w_0.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.6.ffn.ffn.w_in.w_1.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.6.ffn.ffn.w_out.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.6.ffn.layernorm_before_ffn.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.6.self_att.layernorm_before_attention.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.6.self_att.self_attention.attention_out.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.6.self_att.self_attention.project_k.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.6.self_att.self_attention.project_q.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.6.self_att.self_attention.project_v.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.7.ffn.ffn.w_in.w_0.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.7.ffn.ffn.w_in.w_1.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.7.ffn.ffn.w_out.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.7.ffn.layernorm_before_ffn.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.7.self_att.layernorm_before_attention.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.7.self_att.self_attention.attention_out.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.7.self_att.self_attention.project_k.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.7.self_att.self_attention.project_q.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.7.self_att.self_attention.project_v.weight": "pytorch_model-00002-of-00013.bin",
"encoder.layers.8.ffn.ffn.w_in.w_0.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.8.ffn.ffn.w_in.w_1.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.8.ffn.ffn.w_out.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.8.ffn.layernorm_before_ffn.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.8.self_att.layernorm_before_attention.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.8.self_att.self_attention.attention_out.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.8.self_att.self_attention.project_k.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.8.self_att.self_attention.project_q.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.8.self_att.self_attention.project_v.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.9.ffn.ffn.w_in.w_0.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.9.ffn.ffn.w_in.w_1.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.9.ffn.ffn.w_out.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.9.ffn.layernorm_before_ffn.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.9.self_att.layernorm_before_attention.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.9.self_att.self_attention.attention_out.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.9.self_att.self_attention.project_k.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.9.self_att.self_attention.project_q.weight": "pytorch_model-00003-of-00013.bin",
"encoder.layers.9.self_att.self_attention.project_v.weight": "pytorch_model-00003-of-00013.bin",
"encoder.output_layernorm.weight": "pytorch_model-00013-of-00013.bin",
"input_embedding.weight": "pytorch_model-00013-of-00013.bin",
"lm_head.weight": "pytorch_model-00013-of-00013.bin",
"position_bias.relative_attention_bias": "pytorch_model-00013-of-00013.bin",
"segment_embedding.weight": "pytorch_model-00013-of-00013.bin"
}
}
|