jonathansuru commited on
Commit
97a82b1
1 Parent(s): 17c8058

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +6 -42
  2. tokenizer_config.json +11 -1864
special_tokens_map.json CHANGED
@@ -203,27 +203,9 @@
203
  "zho_Hant",
204
  "zul_Latn"
205
  ],
206
- "bos_token": {
207
- "content": "<s>",
208
- "lstrip": false,
209
- "normalized": false,
210
- "rstrip": false,
211
- "single_word": false
212
- },
213
- "cls_token": {
214
- "content": "<s>",
215
- "lstrip": false,
216
- "normalized": false,
217
- "rstrip": false,
218
- "single_word": false
219
- },
220
- "eos_token": {
221
- "content": "</s>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false
226
- },
227
  "mask_token": {
228
  "content": "<mask>",
229
  "lstrip": true,
@@ -231,25 +213,7 @@
231
  "rstrip": false,
232
  "single_word": false
233
  },
234
- "pad_token": {
235
- "content": "<pad>",
236
- "lstrip": false,
237
- "normalized": false,
238
- "rstrip": false,
239
- "single_word": false
240
- },
241
- "sep_token": {
242
- "content": "</s>",
243
- "lstrip": false,
244
- "normalized": false,
245
- "rstrip": false,
246
- "single_word": false
247
- },
248
- "unk_token": {
249
- "content": "<unk>",
250
- "lstrip": false,
251
- "normalized": false,
252
- "rstrip": false,
253
- "single_word": false
254
- }
255
  }
 
203
  "zho_Hant",
204
  "zul_Latn"
205
  ],
206
+ "bos_token": "<s>",
207
+ "cls_token": "<s>",
208
+ "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
209
  "mask_token": {
210
  "content": "<mask>",
211
  "lstrip": true,
 
213
  "rstrip": false,
214
  "single_word": false
215
  },
216
+ "pad_token": "<pad>",
217
+ "sep_token": "</s>",
218
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
219
  }
tokenizer_config.json CHANGED
@@ -1,1878 +1,25 @@
1
  {
2
- "added_tokens_decoder": {
3
- "0": {
4
- "content": "<s>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "<pad>",
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": "<unk>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "256001": {
36
- "content": "ace_Arab",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "256002": {
44
- "content": "ace_Latn",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "256003": {
52
- "content": "acm_Arab",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "256004": {
60
- "content": "acq_Arab",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "256005": {
68
- "content": "aeb_Arab",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "256006": {
76
- "content": "afr_Latn",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "256007": {
84
- "content": "ajp_Arab",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": true
90
- },
91
- "256008": {
92
- "content": "aka_Latn",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": true
98
- },
99
- "256009": {
100
- "content": "amh_Ethi",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": true
106
- },
107
- "256010": {
108
- "content": "apc_Arab",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": true
114
- },
115
- "256011": {
116
- "content": "arb_Arab",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "256012": {
124
- "content": "ars_Arab",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "256013": {
132
- "content": "ary_Arab",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "256014": {
140
- "content": "arz_Arab",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "256015": {
148
- "content": "asm_Beng",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "256016": {
156
- "content": "ast_Latn",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": true
162
- },
163
- "256017": {
164
- "content": "awa_Deva",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": true
170
- },
171
- "256018": {
172
- "content": "ayr_Latn",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "256019": {
180
- "content": "azb_Arab",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- },
187
- "256020": {
188
- "content": "azj_Latn",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": true
194
- },
195
- "256021": {
196
- "content": "bak_Cyrl",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": true
202
- },
203
- "256022": {
204
- "content": "bam_Latn",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": true
210
- },
211
- "256023": {
212
- "content": "ban_Latn",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": true
218
- },
219
- "256024": {
220
- "content": "bel_Cyrl",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": true
226
- },
227
- "256025": {
228
- "content": "bem_Latn",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": true
234
- },
235
- "256026": {
236
- "content": "ben_Beng",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": true
242
- },
243
- "256027": {
244
- "content": "bho_Deva",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": true
250
- },
251
- "256028": {
252
- "content": "bjn_Arab",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": true
258
- },
259
- "256029": {
260
- "content": "bjn_Latn",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": true
266
- },
267
- "256030": {
268
- "content": "bod_Tibt",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": true
274
- },
275
- "256031": {
276
- "content": "bos_Latn",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": true
282
- },
283
- "256032": {
284
- "content": "bug_Latn",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": true
290
- },
291
- "256033": {
292
- "content": "bul_Cyrl",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": true
298
- },
299
- "256034": {
300
- "content": "cat_Latn",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": true
306
- },
307
- "256035": {
308
- "content": "ceb_Latn",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": true
314
- },
315
- "256036": {
316
- "content": "ces_Latn",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": true
322
- },
323
- "256037": {
324
- "content": "cjk_Latn",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": true
330
- },
331
- "256038": {
332
- "content": "ckb_Arab",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": true
338
- },
339
- "256039": {
340
- "content": "crh_Latn",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": true
346
- },
347
- "256040": {
348
- "content": "cym_Latn",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": true
354
- },
355
- "256041": {
356
- "content": "dan_Latn",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": true
362
- },
363
- "256042": {
364
- "content": "deu_Latn",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": true
370
- },
371
- "256043": {
372
- "content": "dik_Latn",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": true
378
- },
379
- "256044": {
380
- "content": "dyu_Latn",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": true
386
- },
387
- "256045": {
388
- "content": "dzo_Tibt",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": true
394
- },
395
- "256046": {
396
- "content": "ell_Grek",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": true
402
- },
403
- "256047": {
404
- "content": "eng_Latn",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": true
410
- },
411
- "256048": {
412
- "content": "epo_Latn",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": true
418
- },
419
- "256049": {
420
- "content": "est_Latn",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": true
426
- },
427
- "256050": {
428
- "content": "eus_Latn",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": true
434
- },
435
- "256051": {
436
- "content": "ewe_Latn",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": true
442
- },
443
- "256052": {
444
- "content": "fao_Latn",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": true
450
- },
451
- "256053": {
452
- "content": "pes_Arab",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": true
458
- },
459
- "256054": {
460
- "content": "fij_Latn",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": true
466
- },
467
- "256055": {
468
- "content": "fin_Latn",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": true
474
- },
475
- "256056": {
476
- "content": "fon_Latn",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": true
482
- },
483
- "256057": {
484
- "content": "fra_Latn",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": true
490
- },
491
- "256058": {
492
- "content": "fur_Latn",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": true
498
- },
499
- "256059": {
500
- "content": "fuv_Latn",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": true
506
- },
507
- "256060": {
508
- "content": "gla_Latn",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": true
514
- },
515
- "256061": {
516
- "content": "gle_Latn",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": true
522
- },
523
- "256062": {
524
- "content": "glg_Latn",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": true
530
- },
531
- "256063": {
532
- "content": "grn_Latn",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": true
538
- },
539
- "256064": {
540
- "content": "guj_Gujr",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": true
546
- },
547
- "256065": {
548
- "content": "hat_Latn",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": true
554
- },
555
- "256066": {
556
- "content": "hau_Latn",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": true
562
- },
563
- "256067": {
564
- "content": "heb_Hebr",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": true
570
- },
571
- "256068": {
572
- "content": "hin_Deva",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": true
578
- },
579
- "256069": {
580
- "content": "hne_Deva",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": true
586
- },
587
- "256070": {
588
- "content": "hrv_Latn",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": true
594
- },
595
- "256071": {
596
- "content": "hun_Latn",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": true
602
- },
603
- "256072": {
604
- "content": "hye_Armn",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": true
610
- },
611
- "256073": {
612
- "content": "ibo_Latn",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": true
618
- },
619
- "256074": {
620
- "content": "ilo_Latn",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": true
626
- },
627
- "256075": {
628
- "content": "ind_Latn",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": true
634
- },
635
- "256076": {
636
- "content": "isl_Latn",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": true
642
- },
643
- "256077": {
644
- "content": "ita_Latn",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": true
650
- },
651
- "256078": {
652
- "content": "jav_Latn",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": true
658
- },
659
- "256079": {
660
- "content": "jpn_Jpan",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": true
666
- },
667
- "256080": {
668
- "content": "kab_Latn",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": true
674
- },
675
- "256081": {
676
- "content": "kac_Latn",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": true
682
- },
683
- "256082": {
684
- "content": "kam_Latn",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": true
690
- },
691
- "256083": {
692
- "content": "kan_Knda",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": true
698
- },
699
- "256084": {
700
- "content": "kas_Arab",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": true
706
- },
707
- "256085": {
708
- "content": "kas_Deva",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": true
714
- },
715
- "256086": {
716
- "content": "kat_Geor",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": true
722
- },
723
- "256087": {
724
- "content": "knc_Arab",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": true
730
- },
731
- "256088": {
732
- "content": "knc_Latn",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": true
738
- },
739
- "256089": {
740
- "content": "kaz_Cyrl",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": true
746
- },
747
- "256090": {
748
- "content": "kbp_Latn",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": true
754
- },
755
- "256091": {
756
- "content": "kea_Latn",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": true
762
- },
763
- "256092": {
764
- "content": "khm_Khmr",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": true
770
- },
771
- "256093": {
772
- "content": "kik_Latn",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": true
778
- },
779
- "256094": {
780
- "content": "kin_Latn",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": true
786
- },
787
- "256095": {
788
- "content": "kir_Cyrl",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": true
794
- },
795
- "256096": {
796
- "content": "kmb_Latn",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": true
802
- },
803
- "256097": {
804
- "content": "kon_Latn",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": true
810
- },
811
- "256098": {
812
- "content": "kor_Hang",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": true
818
- },
819
- "256099": {
820
- "content": "kmr_Latn",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": true
826
- },
827
- "256100": {
828
- "content": "lao_Laoo",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": true
834
- },
835
- "256101": {
836
- "content": "lvs_Latn",
837
- "lstrip": false,
838
- "normalized": false,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": true
842
- },
843
- "256102": {
844
- "content": "lij_Latn",
845
- "lstrip": false,
846
- "normalized": false,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": true
850
- },
851
- "256103": {
852
- "content": "lim_Latn",
853
- "lstrip": false,
854
- "normalized": false,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": true
858
- },
859
- "256104": {
860
- "content": "lin_Latn",
861
- "lstrip": false,
862
- "normalized": false,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": true
866
- },
867
- "256105": {
868
- "content": "lit_Latn",
869
- "lstrip": false,
870
- "normalized": false,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": true
874
- },
875
- "256106": {
876
- "content": "lmo_Latn",
877
- "lstrip": false,
878
- "normalized": false,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": true
882
- },
883
- "256107": {
884
- "content": "ltg_Latn",
885
- "lstrip": false,
886
- "normalized": false,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": true
890
- },
891
- "256108": {
892
- "content": "ltz_Latn",
893
- "lstrip": false,
894
- "normalized": false,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": true
898
- },
899
- "256109": {
900
- "content": "lua_Latn",
901
- "lstrip": false,
902
- "normalized": false,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": true
906
- },
907
- "256110": {
908
- "content": "lug_Latn",
909
- "lstrip": false,
910
- "normalized": false,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": true
914
- },
915
- "256111": {
916
- "content": "luo_Latn",
917
- "lstrip": false,
918
- "normalized": false,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": true
922
- },
923
- "256112": {
924
- "content": "lus_Latn",
925
- "lstrip": false,
926
- "normalized": false,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": true
930
- },
931
- "256113": {
932
- "content": "mag_Deva",
933
- "lstrip": false,
934
- "normalized": false,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": true
938
- },
939
- "256114": {
940
- "content": "mai_Deva",
941
- "lstrip": false,
942
- "normalized": false,
943
- "rstrip": false,
944
- "single_word": false,
945
- "special": true
946
- },
947
- "256115": {
948
- "content": "mal_Mlym",
949
- "lstrip": false,
950
- "normalized": false,
951
- "rstrip": false,
952
- "single_word": false,
953
- "special": true
954
- },
955
- "256116": {
956
- "content": "mar_Deva",
957
- "lstrip": false,
958
- "normalized": false,
959
- "rstrip": false,
960
- "single_word": false,
961
- "special": true
962
- },
963
- "256117": {
964
- "content": "min_Latn",
965
- "lstrip": false,
966
- "normalized": false,
967
- "rstrip": false,
968
- "single_word": false,
969
- "special": true
970
- },
971
- "256118": {
972
- "content": "mkd_Cyrl",
973
- "lstrip": false,
974
- "normalized": false,
975
- "rstrip": false,
976
- "single_word": false,
977
- "special": true
978
- },
979
- "256119": {
980
- "content": "plt_Latn",
981
- "lstrip": false,
982
- "normalized": false,
983
- "rstrip": false,
984
- "single_word": false,
985
- "special": true
986
- },
987
- "256120": {
988
- "content": "mlt_Latn",
989
- "lstrip": false,
990
- "normalized": false,
991
- "rstrip": false,
992
- "single_word": false,
993
- "special": true
994
- },
995
- "256121": {
996
- "content": "mni_Beng",
997
- "lstrip": false,
998
- "normalized": false,
999
- "rstrip": false,
1000
- "single_word": false,
1001
- "special": true
1002
- },
1003
- "256122": {
1004
- "content": "khk_Cyrl",
1005
- "lstrip": false,
1006
- "normalized": false,
1007
- "rstrip": false,
1008
- "single_word": false,
1009
- "special": true
1010
- },
1011
- "256123": {
1012
- "content": "mos_Latn",
1013
- "lstrip": false,
1014
- "normalized": false,
1015
- "rstrip": false,
1016
- "single_word": false,
1017
- "special": true
1018
- },
1019
- "256124": {
1020
- "content": "mri_Latn",
1021
- "lstrip": false,
1022
- "normalized": false,
1023
- "rstrip": false,
1024
- "single_word": false,
1025
- "special": true
1026
- },
1027
- "256125": {
1028
- "content": "zsm_Latn",
1029
- "lstrip": false,
1030
- "normalized": false,
1031
- "rstrip": false,
1032
- "single_word": false,
1033
- "special": true
1034
- },
1035
- "256126": {
1036
- "content": "mya_Mymr",
1037
- "lstrip": false,
1038
- "normalized": false,
1039
- "rstrip": false,
1040
- "single_word": false,
1041
- "special": true
1042
- },
1043
- "256127": {
1044
- "content": "nld_Latn",
1045
- "lstrip": false,
1046
- "normalized": false,
1047
- "rstrip": false,
1048
- "single_word": false,
1049
- "special": true
1050
- },
1051
- "256128": {
1052
- "content": "nno_Latn",
1053
- "lstrip": false,
1054
- "normalized": false,
1055
- "rstrip": false,
1056
- "single_word": false,
1057
- "special": true
1058
- },
1059
- "256129": {
1060
- "content": "nob_Latn",
1061
- "lstrip": false,
1062
- "normalized": false,
1063
- "rstrip": false,
1064
- "single_word": false,
1065
- "special": true
1066
- },
1067
- "256130": {
1068
- "content": "npi_Deva",
1069
- "lstrip": false,
1070
- "normalized": false,
1071
- "rstrip": false,
1072
- "single_word": false,
1073
- "special": true
1074
- },
1075
- "256131": {
1076
- "content": "nso_Latn",
1077
- "lstrip": false,
1078
- "normalized": false,
1079
- "rstrip": false,
1080
- "single_word": false,
1081
- "special": true
1082
- },
1083
- "256132": {
1084
- "content": "nus_Latn",
1085
- "lstrip": false,
1086
- "normalized": false,
1087
- "rstrip": false,
1088
- "single_word": false,
1089
- "special": true
1090
- },
1091
- "256133": {
1092
- "content": "nya_Latn",
1093
- "lstrip": false,
1094
- "normalized": false,
1095
- "rstrip": false,
1096
- "single_word": false,
1097
- "special": true
1098
- },
1099
- "256134": {
1100
- "content": "oci_Latn",
1101
- "lstrip": false,
1102
- "normalized": false,
1103
- "rstrip": false,
1104
- "single_word": false,
1105
- "special": true
1106
- },
1107
- "256135": {
1108
- "content": "gaz_Latn",
1109
- "lstrip": false,
1110
- "normalized": false,
1111
- "rstrip": false,
1112
- "single_word": false,
1113
- "special": true
1114
- },
1115
- "256136": {
1116
- "content": "ory_Orya",
1117
- "lstrip": false,
1118
- "normalized": false,
1119
- "rstrip": false,
1120
- "single_word": false,
1121
- "special": true
1122
- },
1123
- "256137": {
1124
- "content": "pag_Latn",
1125
- "lstrip": false,
1126
- "normalized": false,
1127
- "rstrip": false,
1128
- "single_word": false,
1129
- "special": true
1130
- },
1131
- "256138": {
1132
- "content": "pan_Guru",
1133
- "lstrip": false,
1134
- "normalized": false,
1135
- "rstrip": false,
1136
- "single_word": false,
1137
- "special": true
1138
- },
1139
- "256139": {
1140
- "content": "pap_Latn",
1141
- "lstrip": false,
1142
- "normalized": false,
1143
- "rstrip": false,
1144
- "single_word": false,
1145
- "special": true
1146
- },
1147
- "256140": {
1148
- "content": "pol_Latn",
1149
- "lstrip": false,
1150
- "normalized": false,
1151
- "rstrip": false,
1152
- "single_word": false,
1153
- "special": true
1154
- },
1155
- "256141": {
1156
- "content": "por_Latn",
1157
- "lstrip": false,
1158
- "normalized": false,
1159
- "rstrip": false,
1160
- "single_word": false,
1161
- "special": true
1162
- },
1163
- "256142": {
1164
- "content": "prs_Arab",
1165
- "lstrip": false,
1166
- "normalized": false,
1167
- "rstrip": false,
1168
- "single_word": false,
1169
- "special": true
1170
- },
1171
- "256143": {
1172
- "content": "pbt_Arab",
1173
- "lstrip": false,
1174
- "normalized": false,
1175
- "rstrip": false,
1176
- "single_word": false,
1177
- "special": true
1178
- },
1179
- "256144": {
1180
- "content": "quy_Latn",
1181
- "lstrip": false,
1182
- "normalized": false,
1183
- "rstrip": false,
1184
- "single_word": false,
1185
- "special": true
1186
- },
1187
- "256145": {
1188
- "content": "ron_Latn",
1189
- "lstrip": false,
1190
- "normalized": false,
1191
- "rstrip": false,
1192
- "single_word": false,
1193
- "special": true
1194
- },
1195
- "256146": {
1196
- "content": "run_Latn",
1197
- "lstrip": false,
1198
- "normalized": false,
1199
- "rstrip": false,
1200
- "single_word": false,
1201
- "special": true
1202
- },
1203
- "256147": {
1204
- "content": "rus_Cyrl",
1205
- "lstrip": false,
1206
- "normalized": false,
1207
- "rstrip": false,
1208
- "single_word": false,
1209
- "special": true
1210
- },
1211
- "256148": {
1212
- "content": "sag_Latn",
1213
- "lstrip": false,
1214
- "normalized": false,
1215
- "rstrip": false,
1216
- "single_word": false,
1217
- "special": true
1218
- },
1219
- "256149": {
1220
- "content": "san_Deva",
1221
- "lstrip": false,
1222
- "normalized": false,
1223
- "rstrip": false,
1224
- "single_word": false,
1225
- "special": true
1226
- },
1227
- "256150": {
1228
- "content": "sat_Beng",
1229
- "lstrip": false,
1230
- "normalized": false,
1231
- "rstrip": false,
1232
- "single_word": false,
1233
- "special": true
1234
- },
1235
- "256151": {
1236
- "content": "scn_Latn",
1237
- "lstrip": false,
1238
- "normalized": false,
1239
- "rstrip": false,
1240
- "single_word": false,
1241
- "special": true
1242
- },
1243
- "256152": {
1244
- "content": "shn_Mymr",
1245
- "lstrip": false,
1246
- "normalized": false,
1247
- "rstrip": false,
1248
- "single_word": false,
1249
- "special": true
1250
- },
1251
- "256153": {
1252
- "content": "sin_Sinh",
1253
- "lstrip": false,
1254
- "normalized": false,
1255
- "rstrip": false,
1256
- "single_word": false,
1257
- "special": true
1258
- },
1259
- "256154": {
1260
- "content": "slk_Latn",
1261
- "lstrip": false,
1262
- "normalized": false,
1263
- "rstrip": false,
1264
- "single_word": false,
1265
- "special": true
1266
- },
1267
- "256155": {
1268
- "content": "slv_Latn",
1269
- "lstrip": false,
1270
- "normalized": false,
1271
- "rstrip": false,
1272
- "single_word": false,
1273
- "special": true
1274
- },
1275
- "256156": {
1276
- "content": "smo_Latn",
1277
- "lstrip": false,
1278
- "normalized": false,
1279
- "rstrip": false,
1280
- "single_word": false,
1281
- "special": true
1282
- },
1283
- "256157": {
1284
- "content": "sna_Latn",
1285
- "lstrip": false,
1286
- "normalized": false,
1287
- "rstrip": false,
1288
- "single_word": false,
1289
- "special": true
1290
- },
1291
- "256158": {
1292
- "content": "snd_Arab",
1293
- "lstrip": false,
1294
- "normalized": false,
1295
- "rstrip": false,
1296
- "single_word": false,
1297
- "special": true
1298
- },
1299
- "256159": {
1300
- "content": "som_Latn",
1301
- "lstrip": false,
1302
- "normalized": false,
1303
- "rstrip": false,
1304
- "single_word": false,
1305
- "special": true
1306
- },
1307
- "256160": {
1308
- "content": "sot_Latn",
1309
- "lstrip": false,
1310
- "normalized": false,
1311
- "rstrip": false,
1312
- "single_word": false,
1313
- "special": true
1314
- },
1315
- "256161": {
1316
- "content": "spa_Latn",
1317
- "lstrip": false,
1318
- "normalized": false,
1319
- "rstrip": false,
1320
- "single_word": false,
1321
- "special": true
1322
- },
1323
- "256162": {
1324
- "content": "als_Latn",
1325
- "lstrip": false,
1326
- "normalized": false,
1327
- "rstrip": false,
1328
- "single_word": false,
1329
- "special": true
1330
- },
1331
- "256163": {
1332
- "content": "srd_Latn",
1333
- "lstrip": false,
1334
- "normalized": false,
1335
- "rstrip": false,
1336
- "single_word": false,
1337
- "special": true
1338
- },
1339
- "256164": {
1340
- "content": "srp_Cyrl",
1341
- "lstrip": false,
1342
- "normalized": false,
1343
- "rstrip": false,
1344
- "single_word": false,
1345
- "special": true
1346
- },
1347
- "256165": {
1348
- "content": "ssw_Latn",
1349
- "lstrip": false,
1350
- "normalized": false,
1351
- "rstrip": false,
1352
- "single_word": false,
1353
- "special": true
1354
- },
1355
- "256166": {
1356
- "content": "sun_Latn",
1357
- "lstrip": false,
1358
- "normalized": false,
1359
- "rstrip": false,
1360
- "single_word": false,
1361
- "special": true
1362
- },
1363
- "256167": {
1364
- "content": "swe_Latn",
1365
- "lstrip": false,
1366
- "normalized": false,
1367
- "rstrip": false,
1368
- "single_word": false,
1369
- "special": true
1370
- },
1371
- "256168": {
1372
- "content": "swh_Latn",
1373
- "lstrip": false,
1374
- "normalized": false,
1375
- "rstrip": false,
1376
- "single_word": false,
1377
- "special": true
1378
- },
1379
- "256169": {
1380
- "content": "szl_Latn",
1381
- "lstrip": false,
1382
- "normalized": false,
1383
- "rstrip": false,
1384
- "single_word": false,
1385
- "special": true
1386
- },
1387
- "256170": {
1388
- "content": "tam_Taml",
1389
- "lstrip": false,
1390
- "normalized": false,
1391
- "rstrip": false,
1392
- "single_word": false,
1393
- "special": true
1394
- },
1395
- "256171": {
1396
- "content": "tat_Cyrl",
1397
- "lstrip": false,
1398
- "normalized": false,
1399
- "rstrip": false,
1400
- "single_word": false,
1401
- "special": true
1402
- },
1403
- "256172": {
1404
- "content": "tel_Telu",
1405
- "lstrip": false,
1406
- "normalized": false,
1407
- "rstrip": false,
1408
- "single_word": false,
1409
- "special": true
1410
- },
1411
- "256173": {
1412
- "content": "tgk_Cyrl",
1413
- "lstrip": false,
1414
- "normalized": false,
1415
- "rstrip": false,
1416
- "single_word": false,
1417
- "special": true
1418
- },
1419
- "256174": {
1420
- "content": "tgl_Latn",
1421
- "lstrip": false,
1422
- "normalized": false,
1423
- "rstrip": false,
1424
- "single_word": false,
1425
- "special": true
1426
- },
1427
- "256175": {
1428
- "content": "tha_Thai",
1429
- "lstrip": false,
1430
- "normalized": false,
1431
- "rstrip": false,
1432
- "single_word": false,
1433
- "special": true
1434
- },
1435
- "256176": {
1436
- "content": "tir_Ethi",
1437
- "lstrip": false,
1438
- "normalized": false,
1439
- "rstrip": false,
1440
- "single_word": false,
1441
- "special": true
1442
- },
1443
- "256177": {
1444
- "content": "taq_Latn",
1445
- "lstrip": false,
1446
- "normalized": false,
1447
- "rstrip": false,
1448
- "single_word": false,
1449
- "special": true
1450
- },
1451
- "256178": {
1452
- "content": "taq_Tfng",
1453
- "lstrip": false,
1454
- "normalized": false,
1455
- "rstrip": false,
1456
- "single_word": false,
1457
- "special": true
1458
- },
1459
- "256179": {
1460
- "content": "tpi_Latn",
1461
- "lstrip": false,
1462
- "normalized": false,
1463
- "rstrip": false,
1464
- "single_word": false,
1465
- "special": true
1466
- },
1467
- "256180": {
1468
- "content": "tsn_Latn",
1469
- "lstrip": false,
1470
- "normalized": false,
1471
- "rstrip": false,
1472
- "single_word": false,
1473
- "special": true
1474
- },
1475
- "256181": {
1476
- "content": "tso_Latn",
1477
- "lstrip": false,
1478
- "normalized": false,
1479
- "rstrip": false,
1480
- "single_word": false,
1481
- "special": true
1482
- },
1483
- "256182": {
1484
- "content": "tuk_Latn",
1485
- "lstrip": false,
1486
- "normalized": false,
1487
- "rstrip": false,
1488
- "single_word": false,
1489
- "special": true
1490
- },
1491
- "256183": {
1492
- "content": "tum_Latn",
1493
- "lstrip": false,
1494
- "normalized": false,
1495
- "rstrip": false,
1496
- "single_word": false,
1497
- "special": true
1498
- },
1499
- "256184": {
1500
- "content": "tur_Latn",
1501
- "lstrip": false,
1502
- "normalized": false,
1503
- "rstrip": false,
1504
- "single_word": false,
1505
- "special": true
1506
- },
1507
- "256185": {
1508
- "content": "twi_Latn",
1509
- "lstrip": false,
1510
- "normalized": false,
1511
- "rstrip": false,
1512
- "single_word": false,
1513
- "special": true
1514
- },
1515
- "256186": {
1516
- "content": "tzm_Tfng",
1517
- "lstrip": false,
1518
- "normalized": false,
1519
- "rstrip": false,
1520
- "single_word": false,
1521
- "special": true
1522
- },
1523
- "256187": {
1524
- "content": "uig_Arab",
1525
- "lstrip": false,
1526
- "normalized": false,
1527
- "rstrip": false,
1528
- "single_word": false,
1529
- "special": true
1530
- },
1531
- "256188": {
1532
- "content": "ukr_Cyrl",
1533
- "lstrip": false,
1534
- "normalized": false,
1535
- "rstrip": false,
1536
- "single_word": false,
1537
- "special": true
1538
- },
1539
- "256189": {
1540
- "content": "umb_Latn",
1541
- "lstrip": false,
1542
- "normalized": false,
1543
- "rstrip": false,
1544
- "single_word": false,
1545
- "special": true
1546
- },
1547
- "256190": {
1548
- "content": "urd_Arab",
1549
- "lstrip": false,
1550
- "normalized": false,
1551
- "rstrip": false,
1552
- "single_word": false,
1553
- "special": true
1554
- },
1555
- "256191": {
1556
- "content": "uzn_Latn",
1557
- "lstrip": false,
1558
- "normalized": false,
1559
- "rstrip": false,
1560
- "single_word": false,
1561
- "special": true
1562
- },
1563
- "256192": {
1564
- "content": "vec_Latn",
1565
- "lstrip": false,
1566
- "normalized": false,
1567
- "rstrip": false,
1568
- "single_word": false,
1569
- "special": true
1570
- },
1571
- "256193": {
1572
- "content": "vie_Latn",
1573
- "lstrip": false,
1574
- "normalized": false,
1575
- "rstrip": false,
1576
- "single_word": false,
1577
- "special": true
1578
- },
1579
- "256194": {
1580
- "content": "war_Latn",
1581
- "lstrip": false,
1582
- "normalized": false,
1583
- "rstrip": false,
1584
- "single_word": false,
1585
- "special": true
1586
- },
1587
- "256195": {
1588
- "content": "wol_Latn",
1589
- "lstrip": false,
1590
- "normalized": false,
1591
- "rstrip": false,
1592
- "single_word": false,
1593
- "special": true
1594
- },
1595
- "256196": {
1596
- "content": "xho_Latn",
1597
- "lstrip": false,
1598
- "normalized": false,
1599
- "rstrip": false,
1600
- "single_word": false,
1601
- "special": true
1602
- },
1603
- "256197": {
1604
- "content": "ydd_Hebr",
1605
- "lstrip": false,
1606
- "normalized": false,
1607
- "rstrip": false,
1608
- "single_word": false,
1609
- "special": true
1610
- },
1611
- "256198": {
1612
- "content": "yor_Latn",
1613
- "lstrip": false,
1614
- "normalized": false,
1615
- "rstrip": false,
1616
- "single_word": false,
1617
- "special": true
1618
- },
1619
- "256199": {
1620
- "content": "yue_Hant",
1621
- "lstrip": false,
1622
- "normalized": false,
1623
- "rstrip": false,
1624
- "single_word": false,
1625
- "special": true
1626
- },
1627
- "256200": {
1628
- "content": "zho_Hans",
1629
- "lstrip": false,
1630
- "normalized": false,
1631
- "rstrip": false,
1632
- "single_word": false,
1633
- "special": true
1634
- },
1635
- "256201": {
1636
- "content": "zho_Hant",
1637
- "lstrip": false,
1638
- "normalized": false,
1639
- "rstrip": false,
1640
- "single_word": false,
1641
- "special": true
1642
- },
1643
- "256202": {
1644
- "content": "zul_Latn",
1645
- "lstrip": false,
1646
- "normalized": false,
1647
- "rstrip": false,
1648
- "single_word": false,
1649
- "special": true
1650
- },
1651
- "256203": {
1652
- "content": "<mask>",
1653
- "lstrip": true,
1654
- "normalized": true,
1655
- "rstrip": false,
1656
- "single_word": false,
1657
- "special": true
1658
- }
1659
- },
1660
- "additional_special_tokens": [
1661
- "ace_Arab",
1662
- "ace_Latn",
1663
- "acm_Arab",
1664
- "acq_Arab",
1665
- "aeb_Arab",
1666
- "afr_Latn",
1667
- "ajp_Arab",
1668
- "aka_Latn",
1669
- "amh_Ethi",
1670
- "apc_Arab",
1671
- "arb_Arab",
1672
- "ars_Arab",
1673
- "ary_Arab",
1674
- "arz_Arab",
1675
- "asm_Beng",
1676
- "ast_Latn",
1677
- "awa_Deva",
1678
- "ayr_Latn",
1679
- "azb_Arab",
1680
- "azj_Latn",
1681
- "bak_Cyrl",
1682
- "bam_Latn",
1683
- "ban_Latn",
1684
- "bel_Cyrl",
1685
- "bem_Latn",
1686
- "ben_Beng",
1687
- "bho_Deva",
1688
- "bjn_Arab",
1689
- "bjn_Latn",
1690
- "bod_Tibt",
1691
- "bos_Latn",
1692
- "bug_Latn",
1693
- "bul_Cyrl",
1694
- "cat_Latn",
1695
- "ceb_Latn",
1696
- "ces_Latn",
1697
- "cjk_Latn",
1698
- "ckb_Arab",
1699
- "crh_Latn",
1700
- "cym_Latn",
1701
- "dan_Latn",
1702
- "deu_Latn",
1703
- "dik_Latn",
1704
- "dyu_Latn",
1705
- "dzo_Tibt",
1706
- "ell_Grek",
1707
- "eng_Latn",
1708
- "epo_Latn",
1709
- "est_Latn",
1710
- "eus_Latn",
1711
- "ewe_Latn",
1712
- "fao_Latn",
1713
- "pes_Arab",
1714
- "fij_Latn",
1715
- "fin_Latn",
1716
- "fon_Latn",
1717
- "fra_Latn",
1718
- "fur_Latn",
1719
- "fuv_Latn",
1720
- "gla_Latn",
1721
- "gle_Latn",
1722
- "glg_Latn",
1723
- "grn_Latn",
1724
- "guj_Gujr",
1725
- "hat_Latn",
1726
- "hau_Latn",
1727
- "heb_Hebr",
1728
- "hin_Deva",
1729
- "hne_Deva",
1730
- "hrv_Latn",
1731
- "hun_Latn",
1732
- "hye_Armn",
1733
- "ibo_Latn",
1734
- "ilo_Latn",
1735
- "ind_Latn",
1736
- "isl_Latn",
1737
- "ita_Latn",
1738
- "jav_Latn",
1739
- "jpn_Jpan",
1740
- "kab_Latn",
1741
- "kac_Latn",
1742
- "kam_Latn",
1743
- "kan_Knda",
1744
- "kas_Arab",
1745
- "kas_Deva",
1746
- "kat_Geor",
1747
- "knc_Arab",
1748
- "knc_Latn",
1749
- "kaz_Cyrl",
1750
- "kbp_Latn",
1751
- "kea_Latn",
1752
- "khm_Khmr",
1753
- "kik_Latn",
1754
- "kin_Latn",
1755
- "kir_Cyrl",
1756
- "kmb_Latn",
1757
- "kon_Latn",
1758
- "kor_Hang",
1759
- "kmr_Latn",
1760
- "lao_Laoo",
1761
- "lvs_Latn",
1762
- "lij_Latn",
1763
- "lim_Latn",
1764
- "lin_Latn",
1765
- "lit_Latn",
1766
- "lmo_Latn",
1767
- "ltg_Latn",
1768
- "ltz_Latn",
1769
- "lua_Latn",
1770
- "lug_Latn",
1771
- "luo_Latn",
1772
- "lus_Latn",
1773
- "mag_Deva",
1774
- "mai_Deva",
1775
- "mal_Mlym",
1776
- "mar_Deva",
1777
- "min_Latn",
1778
- "mkd_Cyrl",
1779
- "plt_Latn",
1780
- "mlt_Latn",
1781
- "mni_Beng",
1782
- "khk_Cyrl",
1783
- "mos_Latn",
1784
- "mri_Latn",
1785
- "zsm_Latn",
1786
- "mya_Mymr",
1787
- "nld_Latn",
1788
- "nno_Latn",
1789
- "nob_Latn",
1790
- "npi_Deva",
1791
- "nso_Latn",
1792
- "nus_Latn",
1793
- "nya_Latn",
1794
- "oci_Latn",
1795
- "gaz_Latn",
1796
- "ory_Orya",
1797
- "pag_Latn",
1798
- "pan_Guru",
1799
- "pap_Latn",
1800
- "pol_Latn",
1801
- "por_Latn",
1802
- "prs_Arab",
1803
- "pbt_Arab",
1804
- "quy_Latn",
1805
- "ron_Latn",
1806
- "run_Latn",
1807
- "rus_Cyrl",
1808
- "sag_Latn",
1809
- "san_Deva",
1810
- "sat_Beng",
1811
- "scn_Latn",
1812
- "shn_Mymr",
1813
- "sin_Sinh",
1814
- "slk_Latn",
1815
- "slv_Latn",
1816
- "smo_Latn",
1817
- "sna_Latn",
1818
- "snd_Arab",
1819
- "som_Latn",
1820
- "sot_Latn",
1821
- "spa_Latn",
1822
- "als_Latn",
1823
- "srd_Latn",
1824
- "srp_Cyrl",
1825
- "ssw_Latn",
1826
- "sun_Latn",
1827
- "swe_Latn",
1828
- "swh_Latn",
1829
- "szl_Latn",
1830
- "tam_Taml",
1831
- "tat_Cyrl",
1832
- "tel_Telu",
1833
- "tgk_Cyrl",
1834
- "tgl_Latn",
1835
- "tha_Thai",
1836
- "tir_Ethi",
1837
- "taq_Latn",
1838
- "taq_Tfng",
1839
- "tpi_Latn",
1840
- "tsn_Latn",
1841
- "tso_Latn",
1842
- "tuk_Latn",
1843
- "tum_Latn",
1844
- "tur_Latn",
1845
- "twi_Latn",
1846
- "tzm_Tfng",
1847
- "uig_Arab",
1848
- "ukr_Cyrl",
1849
- "umb_Latn",
1850
- "urd_Arab",
1851
- "uzn_Latn",
1852
- "vec_Latn",
1853
- "vie_Latn",
1854
- "war_Latn",
1855
- "wol_Latn",
1856
- "xho_Latn",
1857
- "ydd_Hebr",
1858
- "yor_Latn",
1859
- "yue_Hant",
1860
- "zho_Hans",
1861
- "zho_Hant",
1862
- "zul_Latn"
1863
- ],
1864
  "bos_token": "<s>",
1865
  "clean_up_tokenization_spaces": true,
1866
  "cls_token": "<s>",
1867
  "eos_token": "</s>",
1868
  "legacy_behaviour": false,
1869
- "mask_token": "<mask>",
 
 
 
 
 
 
 
1870
  "model_max_length": 1024,
1871
  "pad_token": "<pad>",
1872
  "sep_token": "</s>",
1873
  "sp_model_kwargs": {},
1874
- "src_lang": "fra_Latn",
1875
  "tgt_lang": null,
1876
  "tokenizer_class": "NllbTokenizer",
 
1877
  "unk_token": "<unk>"
1878
  }
 
1
  {
2
+ "additional_special_tokens": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "bos_token": "<s>",
4
  "clean_up_tokenization_spaces": true,
5
  "cls_token": "<s>",
6
  "eos_token": "</s>",
7
  "legacy_behaviour": false,
8
+ "mask_token": {
9
+ "__type": "AddedToken",
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
  "model_max_length": 1024,
17
  "pad_token": "<pad>",
18
  "sep_token": "</s>",
19
  "sp_model_kwargs": {},
20
+ "src_lang": null,
21
  "tgt_lang": null,
22
  "tokenizer_class": "NllbTokenizer",
23
+ "tokenizer_file": null,
24
  "unk_token": "<unk>"
25
  }