Xenova HF staff commited on
Commit
b9d0d20
1 Parent(s): bde4e9e

Upload tokenizer.json

Browse files
Files changed (1) hide show
  1. tokenizer.json +938 -1
tokenizer.json CHANGED
@@ -2,7 +2,944 @@
2
  "version": "1.0",
3
  "truncation": null,
4
  "padding": null,
5
- "added_tokens": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "normalizer": {
7
  "type": "Sequence",
8
  "normalizers": [
 
2
  "version": "1.0",
3
  "truncation": null,
4
  "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<s>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<pad>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "</s>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<unk>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 128004,
44
+ "content": "__af__",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 128005,
53
+ "content": "__am__",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 128006,
62
+ "content": "__ar__",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 128007,
71
+ "content": "__ast__",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 128008,
80
+ "content": "__az__",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 128009,
89
+ "content": "__ba__",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 128010,
98
+ "content": "__be__",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 128011,
107
+ "content": "__bg__",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 128012,
116
+ "content": "__bn__",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 128013,
125
+ "content": "__br__",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 128014,
134
+ "content": "__bs__",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 128015,
143
+ "content": "__ca__",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 128016,
152
+ "content": "__ceb__",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 128017,
161
+ "content": "__cs__",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 128018,
170
+ "content": "__cy__",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 128019,
179
+ "content": "__da__",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 128020,
188
+ "content": "__de__",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 128021,
197
+ "content": "__el__",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 128022,
206
+ "content": "__en__",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 128023,
215
+ "content": "__es__",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 128024,
224
+ "content": "__et__",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 128025,
233
+ "content": "__fa__",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 128026,
242
+ "content": "__ff__",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 128027,
251
+ "content": "__fi__",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 128028,
260
+ "content": "__fr__",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 128029,
269
+ "content": "__fy__",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 128030,
278
+ "content": "__ga__",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 128031,
287
+ "content": "__gd__",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 128032,
296
+ "content": "__gl__",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 128033,
305
+ "content": "__gu__",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 128034,
314
+ "content": "__ha__",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 128035,
323
+ "content": "__he__",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 128036,
332
+ "content": "__hi__",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 128037,
341
+ "content": "__hr__",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 128038,
350
+ "content": "__ht__",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 128039,
359
+ "content": "__hu__",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 128040,
368
+ "content": "__hy__",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 128041,
377
+ "content": "__id__",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 128042,
386
+ "content": "__ig__",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 128043,
395
+ "content": "__ilo__",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 128044,
404
+ "content": "__is__",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 128045,
413
+ "content": "__it__",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 128046,
422
+ "content": "__ja__",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 128047,
431
+ "content": "__jv__",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 128048,
440
+ "content": "__ka__",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ },
447
+ {
448
+ "id": 128049,
449
+ "content": "__kk__",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": false,
454
+ "special": true
455
+ },
456
+ {
457
+ "id": 128050,
458
+ "content": "__km__",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": false,
463
+ "special": true
464
+ },
465
+ {
466
+ "id": 128051,
467
+ "content": "__kn__",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": false,
472
+ "special": true
473
+ },
474
+ {
475
+ "id": 128052,
476
+ "content": "__ko__",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": false,
481
+ "special": true
482
+ },
483
+ {
484
+ "id": 128053,
485
+ "content": "__lb__",
486
+ "single_word": false,
487
+ "lstrip": false,
488
+ "rstrip": false,
489
+ "normalized": false,
490
+ "special": true
491
+ },
492
+ {
493
+ "id": 128054,
494
+ "content": "__lg__",
495
+ "single_word": false,
496
+ "lstrip": false,
497
+ "rstrip": false,
498
+ "normalized": false,
499
+ "special": true
500
+ },
501
+ {
502
+ "id": 128055,
503
+ "content": "__ln__",
504
+ "single_word": false,
505
+ "lstrip": false,
506
+ "rstrip": false,
507
+ "normalized": false,
508
+ "special": true
509
+ },
510
+ {
511
+ "id": 128056,
512
+ "content": "__lo__",
513
+ "single_word": false,
514
+ "lstrip": false,
515
+ "rstrip": false,
516
+ "normalized": false,
517
+ "special": true
518
+ },
519
+ {
520
+ "id": 128057,
521
+ "content": "__lt__",
522
+ "single_word": false,
523
+ "lstrip": false,
524
+ "rstrip": false,
525
+ "normalized": false,
526
+ "special": true
527
+ },
528
+ {
529
+ "id": 128058,
530
+ "content": "__lv__",
531
+ "single_word": false,
532
+ "lstrip": false,
533
+ "rstrip": false,
534
+ "normalized": false,
535
+ "special": true
536
+ },
537
+ {
538
+ "id": 128059,
539
+ "content": "__mg__",
540
+ "single_word": false,
541
+ "lstrip": false,
542
+ "rstrip": false,
543
+ "normalized": false,
544
+ "special": true
545
+ },
546
+ {
547
+ "id": 128060,
548
+ "content": "__mk__",
549
+ "single_word": false,
550
+ "lstrip": false,
551
+ "rstrip": false,
552
+ "normalized": false,
553
+ "special": true
554
+ },
555
+ {
556
+ "id": 128061,
557
+ "content": "__ml__",
558
+ "single_word": false,
559
+ "lstrip": false,
560
+ "rstrip": false,
561
+ "normalized": false,
562
+ "special": true
563
+ },
564
+ {
565
+ "id": 128062,
566
+ "content": "__mn__",
567
+ "single_word": false,
568
+ "lstrip": false,
569
+ "rstrip": false,
570
+ "normalized": false,
571
+ "special": true
572
+ },
573
+ {
574
+ "id": 128063,
575
+ "content": "__mr__",
576
+ "single_word": false,
577
+ "lstrip": false,
578
+ "rstrip": false,
579
+ "normalized": false,
580
+ "special": true
581
+ },
582
+ {
583
+ "id": 128064,
584
+ "content": "__ms__",
585
+ "single_word": false,
586
+ "lstrip": false,
587
+ "rstrip": false,
588
+ "normalized": false,
589
+ "special": true
590
+ },
591
+ {
592
+ "id": 128065,
593
+ "content": "__my__",
594
+ "single_word": false,
595
+ "lstrip": false,
596
+ "rstrip": false,
597
+ "normalized": false,
598
+ "special": true
599
+ },
600
+ {
601
+ "id": 128066,
602
+ "content": "__ne__",
603
+ "single_word": false,
604
+ "lstrip": false,
605
+ "rstrip": false,
606
+ "normalized": false,
607
+ "special": true
608
+ },
609
+ {
610
+ "id": 128067,
611
+ "content": "__nl__",
612
+ "single_word": false,
613
+ "lstrip": false,
614
+ "rstrip": false,
615
+ "normalized": false,
616
+ "special": true
617
+ },
618
+ {
619
+ "id": 128068,
620
+ "content": "__no__",
621
+ "single_word": false,
622
+ "lstrip": false,
623
+ "rstrip": false,
624
+ "normalized": false,
625
+ "special": true
626
+ },
627
+ {
628
+ "id": 128069,
629
+ "content": "__ns__",
630
+ "single_word": false,
631
+ "lstrip": false,
632
+ "rstrip": false,
633
+ "normalized": false,
634
+ "special": true
635
+ },
636
+ {
637
+ "id": 128070,
638
+ "content": "__oc__",
639
+ "single_word": false,
640
+ "lstrip": false,
641
+ "rstrip": false,
642
+ "normalized": false,
643
+ "special": true
644
+ },
645
+ {
646
+ "id": 128071,
647
+ "content": "__or__",
648
+ "single_word": false,
649
+ "lstrip": false,
650
+ "rstrip": false,
651
+ "normalized": false,
652
+ "special": true
653
+ },
654
+ {
655
+ "id": 128072,
656
+ "content": "__pa__",
657
+ "single_word": false,
658
+ "lstrip": false,
659
+ "rstrip": false,
660
+ "normalized": false,
661
+ "special": true
662
+ },
663
+ {
664
+ "id": 128073,
665
+ "content": "__pl__",
666
+ "single_word": false,
667
+ "lstrip": false,
668
+ "rstrip": false,
669
+ "normalized": false,
670
+ "special": true
671
+ },
672
+ {
673
+ "id": 128074,
674
+ "content": "__ps__",
675
+ "single_word": false,
676
+ "lstrip": false,
677
+ "rstrip": false,
678
+ "normalized": false,
679
+ "special": true
680
+ },
681
+ {
682
+ "id": 128075,
683
+ "content": "__pt__",
684
+ "single_word": false,
685
+ "lstrip": false,
686
+ "rstrip": false,
687
+ "normalized": false,
688
+ "special": true
689
+ },
690
+ {
691
+ "id": 128076,
692
+ "content": "__ro__",
693
+ "single_word": false,
694
+ "lstrip": false,
695
+ "rstrip": false,
696
+ "normalized": false,
697
+ "special": true
698
+ },
699
+ {
700
+ "id": 128077,
701
+ "content": "__ru__",
702
+ "single_word": false,
703
+ "lstrip": false,
704
+ "rstrip": false,
705
+ "normalized": false,
706
+ "special": true
707
+ },
708
+ {
709
+ "id": 128078,
710
+ "content": "__sd__",
711
+ "single_word": false,
712
+ "lstrip": false,
713
+ "rstrip": false,
714
+ "normalized": false,
715
+ "special": true
716
+ },
717
+ {
718
+ "id": 128079,
719
+ "content": "__si__",
720
+ "single_word": false,
721
+ "lstrip": false,
722
+ "rstrip": false,
723
+ "normalized": false,
724
+ "special": true
725
+ },
726
+ {
727
+ "id": 128080,
728
+ "content": "__sk__",
729
+ "single_word": false,
730
+ "lstrip": false,
731
+ "rstrip": false,
732
+ "normalized": false,
733
+ "special": true
734
+ },
735
+ {
736
+ "id": 128081,
737
+ "content": "__sl__",
738
+ "single_word": false,
739
+ "lstrip": false,
740
+ "rstrip": false,
741
+ "normalized": false,
742
+ "special": true
743
+ },
744
+ {
745
+ "id": 128082,
746
+ "content": "__so__",
747
+ "single_word": false,
748
+ "lstrip": false,
749
+ "rstrip": false,
750
+ "normalized": false,
751
+ "special": true
752
+ },
753
+ {
754
+ "id": 128083,
755
+ "content": "__sq__",
756
+ "single_word": false,
757
+ "lstrip": false,
758
+ "rstrip": false,
759
+ "normalized": false,
760
+ "special": true
761
+ },
762
+ {
763
+ "id": 128084,
764
+ "content": "__sr__",
765
+ "single_word": false,
766
+ "lstrip": false,
767
+ "rstrip": false,
768
+ "normalized": false,
769
+ "special": true
770
+ },
771
+ {
772
+ "id": 128085,
773
+ "content": "__ss__",
774
+ "single_word": false,
775
+ "lstrip": false,
776
+ "rstrip": false,
777
+ "normalized": false,
778
+ "special": true
779
+ },
780
+ {
781
+ "id": 128086,
782
+ "content": "__su__",
783
+ "single_word": false,
784
+ "lstrip": false,
785
+ "rstrip": false,
786
+ "normalized": false,
787
+ "special": true
788
+ },
789
+ {
790
+ "id": 128087,
791
+ "content": "__sv__",
792
+ "single_word": false,
793
+ "lstrip": false,
794
+ "rstrip": false,
795
+ "normalized": false,
796
+ "special": true
797
+ },
798
+ {
799
+ "id": 128088,
800
+ "content": "__sw__",
801
+ "single_word": false,
802
+ "lstrip": false,
803
+ "rstrip": false,
804
+ "normalized": false,
805
+ "special": true
806
+ },
807
+ {
808
+ "id": 128089,
809
+ "content": "__ta__",
810
+ "single_word": false,
811
+ "lstrip": false,
812
+ "rstrip": false,
813
+ "normalized": false,
814
+ "special": true
815
+ },
816
+ {
817
+ "id": 128090,
818
+ "content": "__th__",
819
+ "single_word": false,
820
+ "lstrip": false,
821
+ "rstrip": false,
822
+ "normalized": false,
823
+ "special": true
824
+ },
825
+ {
826
+ "id": 128091,
827
+ "content": "__tl__",
828
+ "single_word": false,
829
+ "lstrip": false,
830
+ "rstrip": false,
831
+ "normalized": false,
832
+ "special": true
833
+ },
834
+ {
835
+ "id": 128092,
836
+ "content": "__tn__",
837
+ "single_word": false,
838
+ "lstrip": false,
839
+ "rstrip": false,
840
+ "normalized": false,
841
+ "special": true
842
+ },
843
+ {
844
+ "id": 128093,
845
+ "content": "__tr__",
846
+ "single_word": false,
847
+ "lstrip": false,
848
+ "rstrip": false,
849
+ "normalized": false,
850
+ "special": true
851
+ },
852
+ {
853
+ "id": 128094,
854
+ "content": "__uk__",
855
+ "single_word": false,
856
+ "lstrip": false,
857
+ "rstrip": false,
858
+ "normalized": false,
859
+ "special": true
860
+ },
861
+ {
862
+ "id": 128095,
863
+ "content": "__ur__",
864
+ "single_word": false,
865
+ "lstrip": false,
866
+ "rstrip": false,
867
+ "normalized": false,
868
+ "special": true
869
+ },
870
+ {
871
+ "id": 128096,
872
+ "content": "__uz__",
873
+ "single_word": false,
874
+ "lstrip": false,
875
+ "rstrip": false,
876
+ "normalized": false,
877
+ "special": true
878
+ },
879
+ {
880
+ "id": 128097,
881
+ "content": "__vi__",
882
+ "single_word": false,
883
+ "lstrip": false,
884
+ "rstrip": false,
885
+ "normalized": false,
886
+ "special": true
887
+ },
888
+ {
889
+ "id": 128098,
890
+ "content": "__wo__",
891
+ "single_word": false,
892
+ "lstrip": false,
893
+ "rstrip": false,
894
+ "normalized": false,
895
+ "special": true
896
+ },
897
+ {
898
+ "id": 128099,
899
+ "content": "__xh__",
900
+ "single_word": false,
901
+ "lstrip": false,
902
+ "rstrip": false,
903
+ "normalized": false,
904
+ "special": true
905
+ },
906
+ {
907
+ "id": 128100,
908
+ "content": "__yi__",
909
+ "single_word": false,
910
+ "lstrip": false,
911
+ "rstrip": false,
912
+ "normalized": false,
913
+ "special": true
914
+ },
915
+ {
916
+ "id": 128101,
917
+ "content": "__yo__",
918
+ "single_word": false,
919
+ "lstrip": false,
920
+ "rstrip": false,
921
+ "normalized": false,
922
+ "special": true
923
+ },
924
+ {
925
+ "id": 128102,
926
+ "content": "__zh__",
927
+ "single_word": false,
928
+ "lstrip": false,
929
+ "rstrip": false,
930
+ "normalized": false,
931
+ "special": true
932
+ },
933
+ {
934
+ "id": 128103,
935
+ "content": "__zu__",
936
+ "single_word": false,
937
+ "lstrip": false,
938
+ "rstrip": false,
939
+ "normalized": false,
940
+ "special": true
941
+ }
942
+ ],
943
  "normalizer": {
944
  "type": "Sequence",
945
  "normalizers": [