tokenizer_config.json
| 1 | { |
| 2 | "added_tokens_decoder": { |
| 3 | "0": { |
| 4 | "content": "<pad>", |
| 5 | "lstrip": false, |
| 6 | "normalized": false, |
| 7 | "rstrip": false, |
| 8 | "single_word": false, |
| 9 | "special": true |
| 10 | }, |
| 11 | "1": { |
| 12 | "content": "<unk>", |
| 13 | "lstrip": false, |
| 14 | "normalized": false, |
| 15 | "rstrip": false, |
| 16 | "single_word": false, |
| 17 | "special": true |
| 18 | }, |
| 19 | "2": { |
| 20 | "content": "<s>", |
| 21 | "lstrip": false, |
| 22 | "normalized": false, |
| 23 | "rstrip": false, |
| 24 | "single_word": false, |
| 25 | "special": true |
| 26 | }, |
| 27 | "3": { |
| 28 | "content": "</s>", |
| 29 | "lstrip": false, |
| 30 | "normalized": false, |
| 31 | "rstrip": false, |
| 32 | "single_word": false, |
| 33 | "special": true |
| 34 | }, |
| 35 | "256001": { |
| 36 | "content": "__afr__", |
| 37 | "lstrip": false, |
| 38 | "normalized": false, |
| 39 | "rstrip": false, |
| 40 | "single_word": false, |
| 41 | "special": true |
| 42 | }, |
| 43 | "256002": { |
| 44 | "content": "__amh__", |
| 45 | "lstrip": false, |
| 46 | "normalized": false, |
| 47 | "rstrip": false, |
| 48 | "single_word": false, |
| 49 | "special": true |
| 50 | }, |
| 51 | "256003": { |
| 52 | "content": "__arb__", |
| 53 | "lstrip": false, |
| 54 | "normalized": false, |
| 55 | "rstrip": false, |
| 56 | "single_word": false, |
| 57 | "special": true |
| 58 | }, |
| 59 | "256004": { |
| 60 | "content": "__ary__", |
| 61 | "lstrip": false, |
| 62 | "normalized": false, |
| 63 | "rstrip": false, |
| 64 | "single_word": false, |
| 65 | "special": true |
| 66 | }, |
| 67 | "256005": { |
| 68 | "content": "__arz__", |
| 69 | "lstrip": false, |
| 70 | "normalized": false, |
| 71 | "rstrip": false, |
| 72 | "single_word": false, |
| 73 | "special": true |
| 74 | }, |
| 75 | "256006": { |
| 76 | "content": "__asm__", |
| 77 | "lstrip": false, |
| 78 | "normalized": false, |
| 79 | "rstrip": false, |
| 80 | "single_word": false, |
| 81 | "special": true |
| 82 | }, |
| 83 | "256007": { |
| 84 | "content": "__azj__", |
| 85 | "lstrip": false, |
| 86 | "normalized": false, |
| 87 | "rstrip": false, |
| 88 | "single_word": false, |
| 89 | "special": true |
| 90 | }, |
| 91 | "256008": { |
| 92 | "content": "__bel__", |
| 93 | "lstrip": false, |
| 94 | "normalized": false, |
| 95 | "rstrip": false, |
| 96 | "single_word": false, |
| 97 | "special": true |
| 98 | }, |
| 99 | "256009": { |
| 100 | "content": "__ben__", |
| 101 | "lstrip": false, |
| 102 | "normalized": false, |
| 103 | "rstrip": false, |
| 104 | "single_word": false, |
| 105 | "special": true |
| 106 | }, |
| 107 | "256010": { |
| 108 | "content": "__bos__", |
| 109 | "lstrip": false, |
| 110 | "normalized": false, |
| 111 | "rstrip": false, |
| 112 | "single_word": false, |
| 113 | "special": true |
| 114 | }, |
| 115 | "256011": { |
| 116 | "content": "__bul__", |
| 117 | "lstrip": false, |
| 118 | "normalized": false, |
| 119 | "rstrip": false, |
| 120 | "single_word": false, |
| 121 | "special": true |
| 122 | }, |
| 123 | "256012": { |
| 124 | "content": "__cat__", |
| 125 | "lstrip": false, |
| 126 | "normalized": false, |
| 127 | "rstrip": false, |
| 128 | "single_word": false, |
| 129 | "special": true |
| 130 | }, |
| 131 | "256013": { |
| 132 | "content": "__ceb__", |
| 133 | "lstrip": false, |
| 134 | "normalized": false, |
| 135 | "rstrip": false, |
| 136 | "single_word": false, |
| 137 | "special": true |
| 138 | }, |
| 139 | "256014": { |
| 140 | "content": "__ces__", |
| 141 | "lstrip": false, |
| 142 | "normalized": false, |
| 143 | "rstrip": false, |
| 144 | "single_word": false, |
| 145 | "special": true |
| 146 | }, |
| 147 | "256015": { |
| 148 | "content": "__ckb__", |
| 149 | "lstrip": false, |
| 150 | "normalized": false, |
| 151 | "rstrip": false, |
| 152 | "single_word": false, |
| 153 | "special": true |
| 154 | }, |
| 155 | "256016": { |
| 156 | "content": "__cmn__", |
| 157 | "lstrip": false, |
| 158 | "normalized": false, |
| 159 | "rstrip": false, |
| 160 | "single_word": false, |
| 161 | "special": true |
| 162 | }, |
| 163 | "256017": { |
| 164 | "content": "__cmn_Hant__", |
| 165 | "lstrip": false, |
| 166 | "normalized": false, |
| 167 | "rstrip": false, |
| 168 | "single_word": false, |
| 169 | "special": true |
| 170 | }, |
| 171 | "256018": { |
| 172 | "content": "__cym__", |
| 173 | "lstrip": false, |
| 174 | "normalized": false, |
| 175 | "rstrip": false, |
| 176 | "single_word": false, |
| 177 | "special": true |
| 178 | }, |
| 179 | "256019": { |
| 180 | "content": "__dan__", |
| 181 | "lstrip": false, |
| 182 | "normalized": false, |
| 183 | "rstrip": false, |
| 184 | "single_word": false, |
| 185 | "special": true |
| 186 | }, |
| 187 | "256020": { |
| 188 | "content": "__deu__", |
| 189 | "lstrip": false, |
| 190 | "normalized": false, |
| 191 | "rstrip": false, |
| 192 | "single_word": false, |
| 193 | "special": true |
| 194 | }, |
| 195 | "256021": { |
| 196 | "content": "__ell__", |
| 197 | "lstrip": false, |
| 198 | "normalized": false, |
| 199 | "rstrip": false, |
| 200 | "single_word": false, |
| 201 | "special": true |
| 202 | }, |
| 203 | "256022": { |
| 204 | "content": "__eng__", |
| 205 | "lstrip": false, |
| 206 | "normalized": false, |
| 207 | "rstrip": false, |
| 208 | "single_word": false, |
| 209 | "special": true |
| 210 | }, |
| 211 | "256023": { |
| 212 | "content": "__est__", |
| 213 | "lstrip": false, |
| 214 | "normalized": false, |
| 215 | "rstrip": false, |
| 216 | "single_word": false, |
| 217 | "special": true |
| 218 | }, |
| 219 | "256024": { |
| 220 | "content": "__eus__", |
| 221 | "lstrip": false, |
| 222 | "normalized": false, |
| 223 | "rstrip": false, |
| 224 | "single_word": false, |
| 225 | "special": true |
| 226 | }, |
| 227 | "256025": { |
| 228 | "content": "__fin__", |
| 229 | "lstrip": false, |
| 230 | "normalized": false, |
| 231 | "rstrip": false, |
| 232 | "single_word": false, |
| 233 | "special": true |
| 234 | }, |
| 235 | "256026": { |
| 236 | "content": "__fra__", |
| 237 | "lstrip": false, |
| 238 | "normalized": false, |
| 239 | "rstrip": false, |
| 240 | "single_word": false, |
| 241 | "special": true |
| 242 | }, |
| 243 | "256027": { |
| 244 | "content": "__fuv__", |
| 245 | "lstrip": false, |
| 246 | "normalized": false, |
| 247 | "rstrip": false, |
| 248 | "single_word": false, |
| 249 | "special": true |
| 250 | }, |
| 251 | "256028": { |
| 252 | "content": "__gaz__", |
| 253 | "lstrip": false, |
| 254 | "normalized": false, |
| 255 | "rstrip": false, |
| 256 | "single_word": false, |
| 257 | "special": true |
| 258 | }, |
| 259 | "256029": { |
| 260 | "content": "__gle__", |
| 261 | "lstrip": false, |
| 262 | "normalized": false, |
| 263 | "rstrip": false, |
| 264 | "single_word": false, |
| 265 | "special": true |
| 266 | }, |
| 267 | "256030": { |
| 268 | "content": "__glg__", |
| 269 | "lstrip": false, |
| 270 | "normalized": false, |
| 271 | "rstrip": false, |
| 272 | "single_word": false, |
| 273 | "special": true |
| 274 | }, |
| 275 | "256031": { |
| 276 | "content": "__guj__", |
| 277 | "lstrip": false, |
| 278 | "normalized": false, |
| 279 | "rstrip": false, |
| 280 | "single_word": false, |
| 281 | "special": true |
| 282 | }, |
| 283 | "256032": { |
| 284 | "content": "__heb__", |
| 285 | "lstrip": false, |
| 286 | "normalized": false, |
| 287 | "rstrip": false, |
| 288 | "single_word": false, |
| 289 | "special": true |
| 290 | }, |
| 291 | "256033": { |
| 292 | "content": "__hin__", |
| 293 | "lstrip": false, |
| 294 | "normalized": false, |
| 295 | "rstrip": false, |
| 296 | "single_word": false, |
| 297 | "special": true |
| 298 | }, |
| 299 | "256034": { |
| 300 | "content": "__hrv__", |
| 301 | "lstrip": false, |
| 302 | "normalized": false, |
| 303 | "rstrip": false, |
| 304 | "single_word": false, |
| 305 | "special": true |
| 306 | }, |
| 307 | "256035": { |
| 308 | "content": "__hun__", |
| 309 | "lstrip": false, |
| 310 | "normalized": false, |
| 311 | "rstrip": false, |
| 312 | "single_word": false, |
| 313 | "special": true |
| 314 | }, |
| 315 | "256036": { |
| 316 | "content": "__hye__", |
| 317 | "lstrip": false, |
| 318 | "normalized": false, |
| 319 | "rstrip": false, |
| 320 | "single_word": false, |
| 321 | "special": true |
| 322 | }, |
| 323 | "256037": { |
| 324 | "content": "__ibo__", |
| 325 | "lstrip": false, |
| 326 | "normalized": false, |
| 327 | "rstrip": false, |
| 328 | "single_word": false, |
| 329 | "special": true |
| 330 | }, |
| 331 | "256038": { |
| 332 | "content": "__ind__", |
| 333 | "lstrip": false, |
| 334 | "normalized": false, |
| 335 | "rstrip": false, |
| 336 | "single_word": false, |
| 337 | "special": true |
| 338 | }, |
| 339 | "256039": { |
| 340 | "content": "__isl__", |
| 341 | "lstrip": false, |
| 342 | "normalized": false, |
| 343 | "rstrip": false, |
| 344 | "single_word": false, |
| 345 | "special": true |
| 346 | }, |
| 347 | "256040": { |
| 348 | "content": "__ita__", |
| 349 | "lstrip": false, |
| 350 | "normalized": false, |
| 351 | "rstrip": false, |
| 352 | "single_word": false, |
| 353 | "special": true |
| 354 | }, |
| 355 | "256041": { |
| 356 | "content": "__jav__", |
| 357 | "lstrip": false, |
| 358 | "normalized": false, |
| 359 | "rstrip": false, |
| 360 | "single_word": false, |
| 361 | "special": true |
| 362 | }, |
| 363 | "256042": { |
| 364 | "content": "__jpn__", |
| 365 | "lstrip": false, |
| 366 | "normalized": false, |
| 367 | "rstrip": false, |
| 368 | "single_word": false, |
| 369 | "special": true |
| 370 | }, |
| 371 | "256043": { |
| 372 | "content": "__kan__", |
| 373 | "lstrip": false, |
| 374 | "normalized": false, |
| 375 | "rstrip": false, |
| 376 | "single_word": false, |
| 377 | "special": true |
| 378 | }, |
| 379 | "256044": { |
| 380 | "content": "__kat__", |
| 381 | "lstrip": false, |
| 382 | "normalized": false, |
| 383 | "rstrip": false, |
| 384 | "single_word": false, |
| 385 | "special": true |
| 386 | }, |
| 387 | "256045": { |
| 388 | "content": "__kaz__", |
| 389 | "lstrip": false, |
| 390 | "normalized": false, |
| 391 | "rstrip": false, |
| 392 | "single_word": false, |
| 393 | "special": true |
| 394 | }, |
| 395 | "256046": { |
| 396 | "content": "__khk__", |
| 397 | "lstrip": false, |
| 398 | "normalized": false, |
| 399 | "rstrip": false, |
| 400 | "single_word": false, |
| 401 | "special": true |
| 402 | }, |
| 403 | "256047": { |
| 404 | "content": "__khm__", |
| 405 | "lstrip": false, |
| 406 | "normalized": false, |
| 407 | "rstrip": false, |
| 408 | "single_word": false, |
| 409 | "special": true |
| 410 | }, |
| 411 | "256048": { |
| 412 | "content": "__kir__", |
| 413 | "lstrip": false, |
| 414 | "normalized": false, |
| 415 | "rstrip": false, |
| 416 | "single_word": false, |
| 417 | "special": true |
| 418 | }, |
| 419 | "256049": { |
| 420 | "content": "__kor__", |
| 421 | "lstrip": false, |
| 422 | "normalized": false, |
| 423 | "rstrip": false, |
| 424 | "single_word": false, |
| 425 | "special": true |
| 426 | }, |
| 427 | "256050": { |
| 428 | "content": "__lao__", |
| 429 | "lstrip": false, |
| 430 | "normalized": false, |
| 431 | "rstrip": false, |
| 432 | "single_word": false, |
| 433 | "special": true |
| 434 | }, |
| 435 | "256051": { |
| 436 | "content": "__lit__", |
| 437 | "lstrip": false, |
| 438 | "normalized": false, |
| 439 | "rstrip": false, |
| 440 | "single_word": false, |
| 441 | "special": true |
| 442 | }, |
| 443 | "256052": { |
| 444 | "content": "__lug__", |
| 445 | "lstrip": false, |
| 446 | "normalized": false, |
| 447 | "rstrip": false, |
| 448 | "single_word": false, |
| 449 | "special": true |
| 450 | }, |
| 451 | "256053": { |
| 452 | "content": "__luo__", |
| 453 | "lstrip": false, |
| 454 | "normalized": false, |
| 455 | "rstrip": false, |
| 456 | "single_word": false, |
| 457 | "special": true |
| 458 | }, |
| 459 | "256054": { |
| 460 | "content": "__lvs__", |
| 461 | "lstrip": false, |
| 462 | "normalized": false, |
| 463 | "rstrip": false, |
| 464 | "single_word": false, |
| 465 | "special": true |
| 466 | }, |
| 467 | "256055": { |
| 468 | "content": "__mai__", |
| 469 | "lstrip": false, |
| 470 | "normalized": false, |
| 471 | "rstrip": false, |
| 472 | "single_word": false, |
| 473 | "special": true |
| 474 | }, |
| 475 | "256056": { |
| 476 | "content": "__mal__", |
| 477 | "lstrip": false, |
| 478 | "normalized": false, |
| 479 | "rstrip": false, |
| 480 | "single_word": false, |
| 481 | "special": true |
| 482 | }, |
| 483 | "256057": { |
| 484 | "content": "__mar__", |
| 485 | "lstrip": false, |
| 486 | "normalized": false, |
| 487 | "rstrip": false, |
| 488 | "single_word": false, |
| 489 | "special": true |
| 490 | }, |
| 491 | "256058": { |
| 492 | "content": "__mkd__", |
| 493 | "lstrip": false, |
| 494 | "normalized": false, |
| 495 | "rstrip": false, |
| 496 | "single_word": false, |
| 497 | "special": true |
| 498 | }, |
| 499 | "256059": { |
| 500 | "content": "__mlt__", |
| 501 | "lstrip": false, |
| 502 | "normalized": false, |
| 503 | "rstrip": false, |
| 504 | "single_word": false, |
| 505 | "special": true |
| 506 | }, |
| 507 | "256060": { |
| 508 | "content": "__mni__", |
| 509 | "lstrip": false, |
| 510 | "normalized": false, |
| 511 | "rstrip": false, |
| 512 | "single_word": false, |
| 513 | "special": true |
| 514 | }, |
| 515 | "256061": { |
| 516 | "content": "__mya__", |
| 517 | "lstrip": false, |
| 518 | "normalized": false, |
| 519 | "rstrip": false, |
| 520 | "single_word": false, |
| 521 | "special": true |
| 522 | }, |
| 523 | "256062": { |
| 524 | "content": "__nld__", |
| 525 | "lstrip": false, |
| 526 | "normalized": false, |
| 527 | "rstrip": false, |
| 528 | "single_word": false, |
| 529 | "special": true |
| 530 | }, |
| 531 | "256063": { |
| 532 | "content": "__nno__", |
| 533 | "lstrip": false, |
| 534 | "normalized": false, |
| 535 | "rstrip": false, |
| 536 | "single_word": false, |
| 537 | "special": true |
| 538 | }, |
| 539 | "256064": { |
| 540 | "content": "__nob__", |
| 541 | "lstrip": false, |
| 542 | "normalized": false, |
| 543 | "rstrip": false, |
| 544 | "single_word": false, |
| 545 | "special": true |
| 546 | }, |
| 547 | "256065": { |
| 548 | "content": "__npi__", |
| 549 | "lstrip": false, |
| 550 | "normalized": false, |
| 551 | "rstrip": false, |
| 552 | "single_word": false, |
| 553 | "special": true |
| 554 | }, |
| 555 | "256066": { |
| 556 | "content": "__nya__", |
| 557 | "lstrip": false, |
| 558 | "normalized": false, |
| 559 | "rstrip": false, |
| 560 | "single_word": false, |
| 561 | "special": true |
| 562 | }, |
| 563 | "256067": { |
| 564 | "content": "__ory__", |
| 565 | "lstrip": false, |
| 566 | "normalized": false, |
| 567 | "rstrip": false, |
| 568 | "single_word": false, |
| 569 | "special": true |
| 570 | }, |
| 571 | "256068": { |
| 572 | "content": "__pan__", |
| 573 | "lstrip": false, |
| 574 | "normalized": false, |
| 575 | "rstrip": false, |
| 576 | "single_word": false, |
| 577 | "special": true |
| 578 | }, |
| 579 | "256069": { |
| 580 | "content": "__pbt__", |
| 581 | "lstrip": false, |
| 582 | "normalized": false, |
| 583 | "rstrip": false, |
| 584 | "single_word": false, |
| 585 | "special": true |
| 586 | }, |
| 587 | "256070": { |
| 588 | "content": "__pes__", |
| 589 | "lstrip": false, |
| 590 | "normalized": false, |
| 591 | "rstrip": false, |
| 592 | "single_word": false, |
| 593 | "special": true |
| 594 | }, |
| 595 | "256071": { |
| 596 | "content": "__pol__", |
| 597 | "lstrip": false, |
| 598 | "normalized": false, |
| 599 | "rstrip": false, |
| 600 | "single_word": false, |
| 601 | "special": true |
| 602 | }, |
| 603 | "256072": { |
| 604 | "content": "__por__", |
| 605 | "lstrip": false, |
| 606 | "normalized": false, |
| 607 | "rstrip": false, |
| 608 | "single_word": false, |
| 609 | "special": true |
| 610 | }, |
| 611 | "256073": { |
| 612 | "content": "__ron__", |
| 613 | "lstrip": false, |
| 614 | "normalized": false, |
| 615 | "rstrip": false, |
| 616 | "single_word": false, |
| 617 | "special": true |
| 618 | }, |
| 619 | "256074": { |
| 620 | "content": "__rus__", |
| 621 | "lstrip": false, |
| 622 | "normalized": false, |
| 623 | "rstrip": false, |
| 624 | "single_word": false, |
| 625 | "special": true |
| 626 | }, |
| 627 | "256075": { |
| 628 | "content": "__sat__", |
| 629 | "lstrip": false, |
| 630 | "normalized": false, |
| 631 | "rstrip": false, |
| 632 | "single_word": false, |
| 633 | "special": true |
| 634 | }, |
| 635 | "256076": { |
| 636 | "content": "__slk__", |
| 637 | "lstrip": false, |
| 638 | "normalized": false, |
| 639 | "rstrip": false, |
| 640 | "single_word": false, |
| 641 | "special": true |
| 642 | }, |
| 643 | "256077": { |
| 644 | "content": "__slv__", |
| 645 | "lstrip": false, |
| 646 | "normalized": false, |
| 647 | "rstrip": false, |
| 648 | "single_word": false, |
| 649 | "special": true |
| 650 | }, |
| 651 | "256078": { |
| 652 | "content": "__sna__", |
| 653 | "lstrip": false, |
| 654 | "normalized": false, |
| 655 | "rstrip": false, |
| 656 | "single_word": false, |
| 657 | "special": true |
| 658 | }, |
| 659 | "256079": { |
| 660 | "content": "__snd__", |
| 661 | "lstrip": false, |
| 662 | "normalized": false, |
| 663 | "rstrip": false, |
| 664 | "single_word": false, |
| 665 | "special": true |
| 666 | }, |
| 667 | "256080": { |
| 668 | "content": "__som__", |
| 669 | "lstrip": false, |
| 670 | "normalized": false, |
| 671 | "rstrip": false, |
| 672 | "single_word": false, |
| 673 | "special": true |
| 674 | }, |
| 675 | "256081": { |
| 676 | "content": "__spa__", |
| 677 | "lstrip": false, |
| 678 | "normalized": false, |
| 679 | "rstrip": false, |
| 680 | "single_word": false, |
| 681 | "special": true |
| 682 | }, |
| 683 | "256082": { |
| 684 | "content": "__srp__", |
| 685 | "lstrip": false, |
| 686 | "normalized": false, |
| 687 | "rstrip": false, |
| 688 | "single_word": false, |
| 689 | "special": true |
| 690 | }, |
| 691 | "256083": { |
| 692 | "content": "__swe__", |
| 693 | "lstrip": false, |
| 694 | "normalized": false, |
| 695 | "rstrip": false, |
| 696 | "single_word": false, |
| 697 | "special": true |
| 698 | }, |
| 699 | "256084": { |
| 700 | "content": "__swh__", |
| 701 | "lstrip": false, |
| 702 | "normalized": false, |
| 703 | "rstrip": false, |
| 704 | "single_word": false, |
| 705 | "special": true |
| 706 | }, |
| 707 | "256085": { |
| 708 | "content": "__tam__", |
| 709 | "lstrip": false, |
| 710 | "normalized": false, |
| 711 | "rstrip": false, |
| 712 | "single_word": false, |
| 713 | "special": true |
| 714 | }, |
| 715 | "256086": { |
| 716 | "content": "__tel__", |
| 717 | "lstrip": false, |
| 718 | "normalized": false, |
| 719 | "rstrip": false, |
| 720 | "single_word": false, |
| 721 | "special": true |
| 722 | }, |
| 723 | "256087": { |
| 724 | "content": "__tgk__", |
| 725 | "lstrip": false, |
| 726 | "normalized": false, |
| 727 | "rstrip": false, |
| 728 | "single_word": false, |
| 729 | "special": true |
| 730 | }, |
| 731 | "256088": { |
| 732 | "content": "__tgl__", |
| 733 | "lstrip": false, |
| 734 | "normalized": false, |
| 735 | "rstrip": false, |
| 736 | "single_word": false, |
| 737 | "special": true |
| 738 | }, |
| 739 | "256089": { |
| 740 | "content": "__tha__", |
| 741 | "lstrip": false, |
| 742 | "normalized": false, |
| 743 | "rstrip": false, |
| 744 | "single_word": false, |
| 745 | "special": true |
| 746 | }, |
| 747 | "256090": { |
| 748 | "content": "__tur__", |
| 749 | "lstrip": false, |
| 750 | "normalized": false, |
| 751 | "rstrip": false, |
| 752 | "single_word": false, |
| 753 | "special": true |
| 754 | }, |
| 755 | "256091": { |
| 756 | "content": "__ukr__", |
| 757 | "lstrip": false, |
| 758 | "normalized": false, |
| 759 | "rstrip": false, |
| 760 | "single_word": false, |
| 761 | "special": true |
| 762 | }, |
| 763 | "256092": { |
| 764 | "content": "__urd__", |
| 765 | "lstrip": false, |
| 766 | "normalized": false, |
| 767 | "rstrip": false, |
| 768 | "single_word": false, |
| 769 | "special": true |
| 770 | }, |
| 771 | "256093": { |
| 772 | "content": "__uzn__", |
| 773 | "lstrip": false, |
| 774 | "normalized": false, |
| 775 | "rstrip": false, |
| 776 | "single_word": false, |
| 777 | "special": true |
| 778 | }, |
| 779 | "256094": { |
| 780 | "content": "__vie__", |
| 781 | "lstrip": false, |
| 782 | "normalized": false, |
| 783 | "rstrip": false, |
| 784 | "single_word": false, |
| 785 | "special": true |
| 786 | }, |
| 787 | "256095": { |
| 788 | "content": "__yor__", |
| 789 | "lstrip": false, |
| 790 | "normalized": false, |
| 791 | "rstrip": false, |
| 792 | "single_word": false, |
| 793 | "special": true |
| 794 | }, |
| 795 | "256096": { |
| 796 | "content": "__yue__", |
| 797 | "lstrip": false, |
| 798 | "normalized": false, |
| 799 | "rstrip": false, |
| 800 | "single_word": false, |
| 801 | "special": true |
| 802 | }, |
| 803 | "256097": { |
| 804 | "content": "__zlm__", |
| 805 | "lstrip": false, |
| 806 | "normalized": false, |
| 807 | "rstrip": false, |
| 808 | "single_word": false, |
| 809 | "special": true |
| 810 | }, |
| 811 | "256098": { |
| 812 | "content": "__zul__", |
| 813 | "lstrip": false, |
| 814 | "normalized": false, |
| 815 | "rstrip": false, |
| 816 | "single_word": false, |
| 817 | "special": true |
| 818 | } |
| 819 | }, |
| 820 | "additional_special_tokens": [ |
| 821 | "__afr__", |
| 822 | "__amh__", |
| 823 | "__arb__", |
| 824 | "__ary__", |
| 825 | "__arz__", |
| 826 | "__asm__", |
| 827 | "__azj__", |
| 828 | "__bel__", |
| 829 | "__ben__", |
| 830 | "__bos__", |
| 831 | "__bul__", |
| 832 | "__cat__", |
| 833 | "__ceb__", |
| 834 | "__ces__", |
| 835 | "__ckb__", |
| 836 | "__cmn__", |
| 837 | "__cmn_Hant__", |
| 838 | "__cym__", |
| 839 | "__dan__", |
| 840 | "__deu__", |
| 841 | "__ell__", |
| 842 | "__eng__", |
| 843 | "__est__", |
| 844 | "__eus__", |
| 845 | "__fin__", |
| 846 | "__fra__", |
| 847 | "__fuv__", |
| 848 | "__gaz__", |
| 849 | "__gle__", |
| 850 | "__glg__", |
| 851 | "__guj__", |
| 852 | "__heb__", |
| 853 | "__hin__", |
| 854 | "__hrv__", |
| 855 | "__hun__", |
| 856 | "__hye__", |
| 857 | "__ibo__", |
| 858 | "__ind__", |
| 859 | "__isl__", |
| 860 | "__ita__", |
| 861 | "__jav__", |
| 862 | "__jpn__", |
| 863 | "__kan__", |
| 864 | "__kat__", |
| 865 | "__kaz__", |
| 866 | "__khk__", |
| 867 | "__khm__", |
| 868 | "__kir__", |
| 869 | "__kor__", |
| 870 | "__lao__", |
| 871 | "__lit__", |
| 872 | "__lug__", |
| 873 | "__luo__", |
| 874 | "__lvs__", |
| 875 | "__mai__", |
| 876 | "__mal__", |
| 877 | "__mar__", |
| 878 | "__mkd__", |
| 879 | "__mlt__", |
| 880 | "__mni__", |
| 881 | "__mya__", |
| 882 | "__nld__", |
| 883 | "__nno__", |
| 884 | "__nob__", |
| 885 | "__npi__", |
| 886 | "__nya__", |
| 887 | "__ory__", |
| 888 | "__pan__", |
| 889 | "__pbt__", |
| 890 | "__pes__", |
| 891 | "__pol__", |
| 892 | "__por__", |
| 893 | "__ron__", |
| 894 | "__rus__", |
| 895 | "__sat__", |
| 896 | "__slk__", |
| 897 | "__slv__", |
| 898 | "__sna__", |
| 899 | "__snd__", |
| 900 | "__som__", |
| 901 | "__spa__", |
| 902 | "__srp__", |
| 903 | "__swe__", |
| 904 | "__swh__", |
| 905 | "__tam__", |
| 906 | "__tel__", |
| 907 | "__tgk__", |
| 908 | "__tgl__", |
| 909 | "__tha__", |
| 910 | "__tur__", |
| 911 | "__ukr__", |
| 912 | "__urd__", |
| 913 | "__uzn__", |
| 914 | "__vie__", |
| 915 | "__yor__", |
| 916 | "__yue__", |
| 917 | "__zlm__", |
| 918 | "__zul__" |
| 919 | ], |
| 920 | "bos_token": "<s>", |
| 921 | "clean_up_tokenization_spaces": true, |
| 922 | "cls_token": "<s>", |
| 923 | "eos_token": "</s>", |
| 924 | "model_max_length": 1000000000000000019884624838656, |
| 925 | "pad_token": "<pad>", |
| 926 | "processor_class": "SeamlessM4TProcessor", |
| 927 | "sep_token": "</s>", |
| 928 | "sp_model_kwargs": {}, |
| 929 | "src_lang": "__eng__", |
| 930 | "tgt_lang": "__fra__", |
| 931 | "tokenizer_class": "SeamlessM4TTokenizer", |
| 932 | "unk_token": "<unk>" |
| 933 | } |
| 934 | |