Instructions to use hf-internal-testing/tiny-processor-seamless_m4t with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hf-internal-testing/tiny-processor-seamless_m4t with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("hf-internal-testing/tiny-processor-seamless_m4t", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "version": "1.0", | |
| "truncation": null, | |
| "padding": null, | |
| "added_tokens": [ | |
| { | |
| "id": 0, | |
| "content": "<pad>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 1, | |
| "content": "<unk>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 2, | |
| "content": "<s>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 3, | |
| "content": "</s>", | |
| "single_word": false, | |
| "lstrip": false, | |
| "rstrip": false, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 504, | |
| "content": "__ace__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 505, | |
| "content": "__ace_Latn__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 506, | |
| "content": "__acm__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 507, | |
| "content": "__acq__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 508, | |
| "content": "__aeb__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 509, | |
| "content": "__afr__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 510, | |
| "content": "__ajp__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 511, | |
| "content": "__aka__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 512, | |
| "content": "__amh__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 513, | |
| "content": "__apc__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 514, | |
| "content": "__arb__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 515, | |
| "content": "__ars__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 516, | |
| "content": "__ary__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 517, | |
| "content": "__arz__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 518, | |
| "content": "__asm__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 519, | |
| "content": "__ast__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 520, | |
| "content": "__awa__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 521, | |
| "content": "__ayr__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 522, | |
| "content": "__azb__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 523, | |
| "content": "__azj__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 524, | |
| "content": "__bak__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 525, | |
| "content": "__bam__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 526, | |
| "content": "__ban__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 527, | |
| "content": "__bel__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 528, | |
| "content": "__bem__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 529, | |
| "content": "__ben__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 530, | |
| "content": "__bho__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 531, | |
| "content": "__bjn__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 532, | |
| "content": "__bjn_Latn__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 533, | |
| "content": "__bod__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 534, | |
| "content": "__bos__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 535, | |
| "content": "__bug__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 536, | |
| "content": "__bul__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 537, | |
| "content": "__cat__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 538, | |
| "content": "__ceb__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 539, | |
| "content": "__ces__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 540, | |
| "content": "__cjk__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 541, | |
| "content": "__ckb__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 542, | |
| "content": "__crh__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 543, | |
| "content": "__cym__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 544, | |
| "content": "__dan__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 545, | |
| "content": "__deu__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 546, | |
| "content": "__dik__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 547, | |
| "content": "__dyu__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 548, | |
| "content": "__dzo__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 549, | |
| "content": "__ell__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 550, | |
| "content": "__eng__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 551, | |
| "content": "__epo__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 552, | |
| "content": "__est__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 553, | |
| "content": "__eus__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 554, | |
| "content": "__ewe__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 555, | |
| "content": "__fao__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 556, | |
| "content": "__pes__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 557, | |
| "content": "__fij__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 558, | |
| "content": "__fin__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 559, | |
| "content": "__fon__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 560, | |
| "content": "__fra__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 561, | |
| "content": "__fur__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 562, | |
| "content": "__fuv__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 563, | |
| "content": "__gla__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 564, | |
| "content": "__gle__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 565, | |
| "content": "__glg__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 566, | |
| "content": "__grn__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 567, | |
| "content": "__guj__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 568, | |
| "content": "__hat__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 569, | |
| "content": "__hau__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 570, | |
| "content": "__heb__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 571, | |
| "content": "__hin__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 572, | |
| "content": "__hne__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 573, | |
| "content": "__hrv__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 574, | |
| "content": "__hun__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 575, | |
| "content": "__hye__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 576, | |
| "content": "__ibo__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 577, | |
| "content": "__ilo__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 578, | |
| "content": "__ind__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 579, | |
| "content": "__isl__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 580, | |
| "content": "__ita__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 581, | |
| "content": "__jav__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 582, | |
| "content": "__jpn__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 583, | |
| "content": "__kab__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 584, | |
| "content": "__kac__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 585, | |
| "content": "__kam__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 586, | |
| "content": "__kan__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 587, | |
| "content": "__kas__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 588, | |
| "content": "__kas_Deva__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 589, | |
| "content": "__kat__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 590, | |
| "content": "__knc__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 591, | |
| "content": "__knc_Latn__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 592, | |
| "content": "__kaz__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 593, | |
| "content": "__kbp__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 594, | |
| "content": "__kea__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 595, | |
| "content": "__khm__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 596, | |
| "content": "__kik__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 597, | |
| "content": "__kin__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 598, | |
| "content": "__kir__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 599, | |
| "content": "__kmb__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 600, | |
| "content": "__kon__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 601, | |
| "content": "__kor__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 602, | |
| "content": "__kmr__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 603, | |
| "content": "__lao__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 604, | |
| "content": "__lvs__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 605, | |
| "content": "__lij__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 606, | |
| "content": "__lim__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 607, | |
| "content": "__lin__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 608, | |
| "content": "__lit__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 609, | |
| "content": "__lmo__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 610, | |
| "content": "__ltg__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 611, | |
| "content": "__ltz__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 612, | |
| "content": "__lua__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 613, | |
| "content": "__lug__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 614, | |
| "content": "__luo__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 615, | |
| "content": "__lus__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 616, | |
| "content": "__mag__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 617, | |
| "content": "__mai__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 618, | |
| "content": "__mal__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 619, | |
| "content": "__mar__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 620, | |
| "content": "__min__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 621, | |
| "content": "__mkd__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 622, | |
| "content": "__plt__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 623, | |
| "content": "__mlt__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 624, | |
| "content": "__mni__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 625, | |
| "content": "__khk__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 626, | |
| "content": "__mos__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 627, | |
| "content": "__mri__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 628, | |
| "content": "__zsm__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 629, | |
| "content": "__mya__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 630, | |
| "content": "__nld__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 631, | |
| "content": "__nno__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 632, | |
| "content": "__nob__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 633, | |
| "content": "__npi__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 634, | |
| "content": "__nso__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 635, | |
| "content": "__nus__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 636, | |
| "content": "__nya__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 637, | |
| "content": "__oci__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 638, | |
| "content": "__gaz__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 639, | |
| "content": "__ory__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 640, | |
| "content": "__pag__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 641, | |
| "content": "__pan__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 642, | |
| "content": "__pap__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 643, | |
| "content": "__pol__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 644, | |
| "content": "__por__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 645, | |
| "content": "__prs__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 646, | |
| "content": "__pbt__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 647, | |
| "content": "__quy__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 648, | |
| "content": "__ron__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 649, | |
| "content": "__run__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 650, | |
| "content": "__rus__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 651, | |
| "content": "__sag__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 652, | |
| "content": "__san__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 653, | |
| "content": "__sat__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 654, | |
| "content": "__scn__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 655, | |
| "content": "__shn__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 656, | |
| "content": "__sin__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 657, | |
| "content": "__slk__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 658, | |
| "content": "__slv__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 659, | |
| "content": "__smo__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 660, | |
| "content": "__sna__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 661, | |
| "content": "__snd__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 662, | |
| "content": "__som__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 663, | |
| "content": "__sot__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 664, | |
| "content": "__spa__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 665, | |
| "content": "__als__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 666, | |
| "content": "__srd__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 667, | |
| "content": "__srp__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 668, | |
| "content": "__ssw__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 669, | |
| "content": "__sun__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 670, | |
| "content": "__swe__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 671, | |
| "content": "__swh__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 672, | |
| "content": "__szl__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 673, | |
| "content": "__tam__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 674, | |
| "content": "__tat__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 675, | |
| "content": "__tel__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 676, | |
| "content": "__tgk__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 677, | |
| "content": "__tgl__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 678, | |
| "content": "__tha__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 679, | |
| "content": "__tir__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 680, | |
| "content": "__taq__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 681, | |
| "content": "__taq_Tfng__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 682, | |
| "content": "__tpi__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 683, | |
| "content": "__tsn__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 684, | |
| "content": "__tso__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 685, | |
| "content": "__tuk__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 686, | |
| "content": "__tum__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 687, | |
| "content": "__tur__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 688, | |
| "content": "__twi__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 689, | |
| "content": "__tzm__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 690, | |
| "content": "__uig__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 691, | |
| "content": "__ukr__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 692, | |
| "content": "__umb__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 693, | |
| "content": "__urd__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 694, | |
| "content": "__uzn__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 695, | |
| "content": "__vec__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 696, | |
| "content": "__vie__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 697, | |
| "content": "__war__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 698, | |
| "content": "__wol__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 699, | |
| "content": "__xho__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 700, | |
| "content": "__ydd__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 701, | |
| "content": "__yor__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 702, | |
| "content": "__yue__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 703, | |
| "content": "__cmn__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 704, | |
| "content": "__cmn_Hant__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| }, | |
| { | |
| "id": 705, | |
| "content": "__zul__", | |
| "single_word": false, | |
| "lstrip": true, | |
| "rstrip": true, | |
| "normalized": false, | |
| "special": true | |
| } | |
| ], | |
| "normalizer": { | |
| "type": "Sequence", | |
| "normalizers": [ | |
| { | |
| "type": "Replace", | |
| "pattern": { | |
| "Regex": "[\\n\\r\\t]" | |
| }, | |
| "content": " " | |
| }, | |
| { | |
| "type": "NFKC" | |
| }, | |
| { | |
| "type": "Strip", | |
| "strip_left": false, | |
| "strip_right": true | |
| }, | |
| { | |
| "type": "Replace", | |
| "pattern": { | |
| "Regex": " +▁" | |
| }, | |
| "content": "▁" | |
| }, | |
| { | |
| "type": "Replace", | |
| "pattern": { | |
| "Regex": "^▁+$" | |
| }, | |
| "content": "" | |
| }, | |
| { | |
| "type": "Replace", | |
| "pattern": { | |
| "Regex": " {2,}" | |
| }, | |
| "content": "▁" | |
| } | |
| ] | |
| }, | |
| "pre_tokenizer": { | |
| "type": "Metaspace", | |
| "replacement": "▁", | |
| "prepend_scheme": "first", | |
| "split": true | |
| }, | |
| "post_processor": { | |
| "type": "TemplateProcessing", | |
| "single": [ | |
| { | |
| "SpecialToken": { | |
| "id": "</s>", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "__fra__", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "</s>", | |
| "type_id": 0 | |
| } | |
| } | |
| ], | |
| "pair": [ | |
| { | |
| "SpecialToken": { | |
| "id": "</s>", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "__fra__", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "A", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "Sequence": { | |
| "id": "B", | |
| "type_id": 0 | |
| } | |
| }, | |
| { | |
| "SpecialToken": { | |
| "id": "</s>", | |
| "type_id": 0 | |
| } | |
| } | |
| ], | |
| "special_tokens": { | |
| "</s>": { | |
| "id": "</s>", | |
| "ids": [ | |
| 3 | |
| ], | |
| "tokens": [ | |
| "</s>" | |
| ] | |
| }, | |
| "__fra__": { | |
| "id": "__fra__", | |
| "ids": [ | |
| 560 | |
| ], | |
| "tokens": [ | |
| "__fra__" | |
| ] | |
| } | |
| } | |
| }, | |
| "decoder": { | |
| "type": "Metaspace", | |
| "replacement": "▁", | |
| "prepend_scheme": "first", | |
| "split": true | |
| }, | |
| "model": { | |
| "type": "BPE", | |
| "dropout": null, | |
| "unk_token": "<unk>", | |
| "continuing_subword_prefix": null, | |
| "end_of_word_suffix": null, | |
| "fuse_unk": true, | |
| "byte_fallback": false, | |
| "ignore_merges": false, | |
| "vocab": { | |
| "<pad>": 0, | |
| "<unk>": 1, | |
| "<s>": 2, | |
| "</s>": 3, | |
| "an": 4, | |
| "▁n": 5, | |
| "▁m": 6, | |
| "▁t": 7, | |
| "▁k": 8, | |
| "▁a": 9, | |
| "▁s": 10, | |
| "en": 11, | |
| "in": 12, | |
| "▁d": 13, | |
| "er": 14, | |
| "la": 15, | |
| "▁b": 16, | |
| "▁p": 17, | |
| "on": 18, | |
| "ar": 19, | |
| "at": 20, | |
| "is": 21, | |
| "le": 22, | |
| "▁e": 23, | |
| "un": 24, | |
| "li": 25, | |
| "▁o": 26, | |
| "▁v": 27, | |
| "▁h": 28, | |
| "▁c": 29, | |
| "▁i": 30, | |
| "ak": 31, | |
| "as": 32, | |
| "es": 33, | |
| "am": 34, | |
| "▁y": 35, | |
| "it": 36, | |
| "or": 37, | |
| "▁g": 38, | |
| "et": 39, | |
| "▁w": 40, | |
| "al": 41, | |
| "▁f": 42, | |
| "AT": 43, | |
| "IN": 44, | |
| "▁<": 45, | |
| "ED": 46, | |
| "ATA": 47, | |
| "MIN": 48, | |
| "DATA": 49, | |
| "MINED": 50, | |
| "▁r": 51, | |
| "ir": 52, | |
| "ang": 53, | |
| "ti": 54, | |
| "▁l": 55, | |
| "ad": 56, | |
| "os": 57, | |
| "om": 58, | |
| "ur": 59, | |
| "el": 60, | |
| "▁j": 61, | |
| "▁na": 62, | |
| "us": 63, | |
| "em": 64, | |
| "ch": 65, | |
| "ik": 66, | |
| "um": 67, | |
| "ga": 68, | |
| "▁\"": 69, | |
| "▁A": 70, | |
| "ta": 71, | |
| "▁M": 72, | |
| "il": 73, | |
| "▁ا": 74, | |
| "im": 75, | |
| "ed": 76, | |
| "ek": 77, | |
| "▁u": 78, | |
| "▁de": 79, | |
| "wa": 80, | |
| "▁.": 81, | |
| "▁la": 82, | |
| "▁S": 83, | |
| "▁N": 84, | |
| "id": 85, | |
| "te": 86, | |
| "ing": 87, | |
| "ay": 88, | |
| "▁-": 89, | |
| "▁ku": 90, | |
| "ok": 91, | |
| "ra": 92, | |
| "ol": 93, | |
| "▁1": 94, | |
| "▁ب": 95, | |
| "▁le": 96, | |
| "ia": 97, | |
| "▁K": 98, | |
| "▁ka": 99, | |
| "▁z": 100, | |
| "uk": 101, | |
| "ha": 102, | |
| "ba": 103, | |
| "▁(": 104, | |
| "ut": 105, | |
| "на": 106, | |
| "da": 107, | |
| "▁in": 108, | |
| "▁T": 109, | |
| "he": 110, | |
| "▁an": 111, | |
| "▁ma": 112, | |
| "▁م": 113, | |
| "▁B": 114, | |
| "ya": 115, | |
| "ie": 116, | |
| "▁I": 117, | |
| "ul": 118, | |
| "re": 119, | |
| "▁с": 120, | |
| "▁P": 121, | |
| "▁D": 122, | |
| "▁क": 123, | |
| "ot": 124, | |
| "ana": 125, | |
| "▁E": 126, | |
| "▁sa": 127, | |
| "▁б": 128, | |
| "od": 129, | |
| "▁se": 130, | |
| "▁pr": 131, | |
| "та": 132, | |
| "▁ta": 133, | |
| "▁ک": 134, | |
| "▁q": 135, | |
| "ان": 136, | |
| "▁к": 137, | |
| "ent": 138, | |
| "ov": 139, | |
| "▁2": 140, | |
| "▁و": 141, | |
| "▁п": 142, | |
| "hi": 143, | |
| "да": 144, | |
| "di": 145, | |
| "▁,": 146, | |
| "ag": 147, | |
| "st": 148, | |
| "ci": 149, | |
| "▁di": 150, | |
| "ap": 151, | |
| "▁C": 152, | |
| "▁en": 153, | |
| "ра": 154, | |
| "▁L": 155, | |
| "▁J": 156, | |
| "de": 157, | |
| "▁ni": 158, | |
| "▁un": 159, | |
| "▁ya": 160, | |
| "▁ba": 161, | |
| "ka": 162, | |
| "ng": 163, | |
| "▁د": 164, | |
| "ен": 165, | |
| "▁H": 166, | |
| "▁ne": 167, | |
| "ла": 168, | |
| "na": 169, | |
| "▁da": 170, | |
| "si": 171, | |
| "▁te": 172, | |
| "ho": 173, | |
| "ri": 174, | |
| "▁ng": 175, | |
| "ong": 176, | |
| "▁li": 177, | |
| "▁ت": 178, | |
| "▁м": 179, | |
| "eng": 180, | |
| "bi": 181, | |
| "og": 182, | |
| "we": 183, | |
| "ma": 184, | |
| "aka": 185, | |
| "tu": 186, | |
| "ye": 187, | |
| "ara": 188, | |
| "..": 189, | |
| "and": 190, | |
| "▁в": 191, | |
| "{{": 192, | |
| "▁O": 193, | |
| "▁स": 194, | |
| "ار": 195, | |
| "▁qu": 196, | |
| "ja": 197, | |
| "▁Y": 198, | |
| "ig": 199, | |
| "▁wa": 200, | |
| "se": 201, | |
| "▁to": 202, | |
| "ku": 203, | |
| "za": 204, | |
| "то": 205, | |
| "▁ti": 206, | |
| "zi": 207, | |
| "to": 208, | |
| "sa": 209, | |
| "eg": 210, | |
| "▁{{": 211, | |
| "▁G": 212, | |
| "▁и": 213, | |
| "\".": 214, | |
| "те": 215, | |
| "▁mu": 216, | |
| "▁о": 217, | |
| "▁а": 218, | |
| "▁si": 219, | |
| "op": 220, | |
| "▁ह": 221, | |
| "be": 222, | |
| "ung": 223, | |
| "не": 224, | |
| "ou": 225, | |
| "va": 226, | |
| "▁ه": 227, | |
| "▁ch": 228, | |
| "▁д": 229, | |
| "▁at": 230, | |
| "ina": 231, | |
| "ва": 232, | |
| "▁th": 233, | |
| "ни": 234, | |
| "▁al": 235, | |
| "▁س": 236, | |
| "▁ل": 237, | |
| "▁'": 238, | |
| "▁me": 239, | |
| "ni": 240, | |
| "▁ال": 241, | |
| "▁ن": 242, | |
| "▁з": 243, | |
| "ati": 244, | |
| "▁ha": 245, | |
| "▁W": 246, | |
| "ud": 247, | |
| "▁is": 248, | |
| "ke": 249, | |
| "▁R": 250, | |
| "▁म": 251, | |
| "yo": 252, | |
| "ua": 253, | |
| "▁no": 254, | |
| "▁на": 255, | |
| "je": 256, | |
| "ти": 257, | |
| "ata": 258, | |
| "▁am": 259, | |
| "▁V": 260, | |
| "▁U": 261, | |
| "▁ko": 262, | |
| "▁प": 263, | |
| "▁ke": 264, | |
| "ро": 265, | |
| "ре": 266, | |
| "ob": 267, | |
| "ter": 268, | |
| "но": 269, | |
| "ani": 270, | |
| "ce": 271, | |
| "▁re": 272, | |
| "pa": 273, | |
| "ne": 274, | |
| "ere": 275, | |
| "bu": 276, | |
| "▁F": 277, | |
| "pe": 278, | |
| "ve": 279, | |
| "▁be": 280, | |
| "▁on": 281, | |
| "ال": 282, | |
| "▁ar": 283, | |
| "...": 284, | |
| "▁ak": 285, | |
| "ка": 286, | |
| "▁va": 287, | |
| "ли": 288, | |
| "ari": 289, | |
| "ist": 290, | |
| "lar": 291, | |
| "ama": 292, | |
| "ри": 293, | |
| "ini": 294, | |
| "▁nga": 295, | |
| "▁tr": 296, | |
| "▁ئ": 297, | |
| "bo": 298, | |
| "्य": 299, | |
| "hu": 300, | |
| "▁ر": 301, | |
| "ant": 302, | |
| "▁je": 303, | |
| "ona": 304, | |
| "ле": 305, | |
| "era": 306, | |
| "ki": 307, | |
| "▁pa": 308, | |
| "ས་": 309, | |
| "▁20": 310, | |
| "▁per": 311, | |
| "ro": 312, | |
| "ны": 313, | |
| "ca": 314, | |
| "▁3": 315, | |
| "▁mo": 316, | |
| "▁mi": 317, | |
| "▁ny": 318, | |
| "ika": 319, | |
| "ji": 320, | |
| "ada": 321, | |
| "га": 322, | |
| "end": 323, | |
| "▁so": 324, | |
| "▁अ": 325, | |
| "ст": 326, | |
| "▁su": 327, | |
| "▁پ": 328, | |
| "▁א": 329, | |
| "▁bi": 330, | |
| "ма": 331, | |
| "ون": 332, | |
| "isa": 333, | |
| "▁tu": 334, | |
| "▁es": 335, | |
| "▁el": 336, | |
| "▁ki": 337, | |
| "me": 338, | |
| "▁đ": 339, | |
| "▁que": 340, | |
| "wo": 341, | |
| "▁er": 342, | |
| "го": 343, | |
| "▁st": 344, | |
| "ita": 345, | |
| "lo": 346, | |
| "wi": 347, | |
| "ug": 348, | |
| "▁the": 349, | |
| "▁ج": 350, | |
| "▁for": 351, | |
| "▁त": 352, | |
| "ko": 353, | |
| "est": 354, | |
| "▁у": 355, | |
| "vi": 356, | |
| "▁ब": 357, | |
| "ای": 358, | |
| "▁do": 359, | |
| "ene": 360, | |
| "▁ش": 361, | |
| "▁ga": 362, | |
| "▁con": 363, | |
| "▁ж": 364, | |
| "▁ف": 365, | |
| "▁по": 366, | |
| "▁ye": 367, | |
| "▁ي": 368, | |
| "ny": 369, | |
| "ane": 370, | |
| "ི་": 371, | |
| "ze": 372, | |
| "▁fa": 373, | |
| "▁ق": 374, | |
| "्र": 375, | |
| "ло": 376, | |
| "ira": 377, | |
| "vo": 378, | |
| "ست": 379, | |
| "ко": 380, | |
| "▁ज": 381, | |
| "▁vi": 382, | |
| "ند": 383, | |
| "up": 384, | |
| "▁?": 385, | |
| "▁आ": 386, | |
| "ང་": 387, | |
| "▁as": 388, | |
| "uma": 389, | |
| "▁po": 390, | |
| "ер": 391, | |
| "ine": 392, | |
| "▁за": 393, | |
| "▁أ": 394, | |
| "ور": 395, | |
| "▁خ": 396, | |
| "▁x": 397, | |
| "▁т": 398, | |
| "▁kan": 399, | |
| "ena": 400, | |
| "nd": 401, | |
| "▁да": 402, | |
| "▁bo": 403, | |
| "ic": 404, | |
| "▁go": 405, | |
| "ver": 406, | |
| "eh": 407, | |
| "▁آ": 408, | |
| "▁ra": 409, | |
| "▁et": 410, | |
| "▁og": 411, | |
| "▁é": 412, | |
| "▁par": 413, | |
| "▁ho": 414, | |
| "asi": 415, | |
| "asa": 416, | |
| "▁ה": 417, | |
| "▁ع": 418, | |
| "th": 419, | |
| "ार": 420, | |
| "ib": 421, | |
| "▁न": 422, | |
| "▁ja": 423, | |
| "qu": 424, | |
| "▁그": 425, | |
| "isi": 426, | |
| "so": 427, | |
| "any": 428, | |
| "ova": 429, | |
| "eni": 430, | |
| "▁ol": 431, | |
| "ele": 432, | |
| "во": 433, | |
| "ind": 434, | |
| "▁hi": 435, | |
| "▁4": 436, | |
| "▁lo": 437, | |
| "▁ба": 438, | |
| "▁men": 439, | |
| "▁ve": 440, | |
| "▁19": 441, | |
| "oni": 442, | |
| "gi": 443, | |
| "ام": 444, | |
| "lam": 445, | |
| "pr": 446, | |
| "ры": 447, | |
| "▁za": 448, | |
| "po": 449, | |
| "▁com": 450, | |
| "▁ك": 451, | |
| "▁of": 452, | |
| "▁та": 453, | |
| "▁द": 454, | |
| "▁ag": 455, | |
| "▁im": 456, | |
| "ու": 457, | |
| "iri": 458, | |
| "olo": 459, | |
| "00": 460, | |
| "▁ক": 461, | |
| "▁du": 462, | |
| "are": 463, | |
| "no": 464, | |
| "ین": 465, | |
| "ို": 466, | |
| "▁не": 467, | |
| "ts": 468, | |
| "han": 469, | |
| "iti": 470, | |
| "ات": 471, | |
| "eri": 472, | |
| "лы": 473, | |
| "lu": 474, | |
| "▁व": 475, | |
| "ab": 476, | |
| "▁ang": 477, | |
| "ore": 478, | |
| "ge": 479, | |
| "tr": 480, | |
| "▁5": 481, | |
| "pi": 482, | |
| "▁के": 483, | |
| "▁dan": 484, | |
| "்க": 485, | |
| "yi": 486, | |
| "ди": 487, | |
| "ju": 488, | |
| "де": 489, | |
| "▁nd": 490, | |
| "▁τ": 491, | |
| "▁man": 492, | |
| "ula": 493, | |
| "▁ш": 494, | |
| "kan": 495, | |
| "iz": 496, | |
| "اد": 497, | |
| "fa": 498, | |
| "una": 499, | |
| "adi": 500, | |
| "▁х": 501, | |
| "ate": 502, | |
| "니다": 503 | |
| }, | |
| "merges": [ | |
| [ | |
| "MIN", | |
| "ED" | |
| ], | |
| [ | |
| "▁n", | |
| "ga" | |
| ], | |
| [ | |
| "▁p", | |
| "er" | |
| ], | |
| [ | |
| "▁t", | |
| "he" | |
| ], | |
| [ | |
| "▁f", | |
| "or" | |
| ], | |
| [ | |
| "▁c", | |
| "on" | |
| ], | |
| [ | |
| "▁k", | |
| "an" | |
| ], | |
| [ | |
| "▁p", | |
| "ar" | |
| ], | |
| [ | |
| "▁m", | |
| "en" | |
| ], | |
| [ | |
| "▁c", | |
| "om" | |
| ], | |
| [ | |
| "▁a", | |
| "ng" | |
| ], | |
| [ | |
| "▁d", | |
| "an" | |
| ], | |
| [ | |
| "▁m", | |
| "an" | |
| ] | |
| ] | |
| } | |
| } |