HoangLe1312 commited on
Commit
dd59971
1 Parent(s): d688bc8

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +14 -3
  2. tokenizer.json +2 -2
  3. tokenizer_config.json +660 -965
special_tokens_map.json CHANGED
@@ -1,20 +1,31 @@
1
  {
 
 
 
 
2
  "bos_token": {
3
- "content": "<|begin_of_text|>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "<|end_of_text|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "<|end_of_text|>",
 
 
 
 
 
 
 
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<start_of_turn>",
4
+ "<end_of_turn>"
5
+ ],
6
  "bos_token": {
7
+ "content": "<bos>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
11
  "single_word": false
12
  },
13
  "eos_token": {
14
+ "content": "<eos>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false
19
  },
20
  "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52b583ee1699c6ca4468f70885bd5f96dd1f7517292362a67581038afc04f4d8
3
- size 9085671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15eb04bc5ad609fb26533e8525302c5640a945e5f67f65b7c849900acda7d99
3
+ size 17518497
tokenizer_config.json CHANGED
@@ -1,2063 +1,1758 @@
1
  {
 
 
2
  "added_tokens_decoder": {
3
- "128000": {
4
- "content": "<|begin_of_text|>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "128001": {
12
- "content": "<|end_of_text|>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "128002": {
20
- "content": "<|reserved_special_token_0|>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
- "128003": {
28
- "content": "<|reserved_special_token_1|>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "128004": {
36
- "content": "<|reserved_special_token_2|>",
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
- "special": true
42
  },
43
- "128005": {
44
- "content": "<|reserved_special_token_3|>",
45
  "lstrip": false,
46
  "normalized": false,
47
  "rstrip": false,
48
  "single_word": false,
49
- "special": true
50
  },
51
- "128006": {
52
- "content": "<|start_header_id|>",
53
  "lstrip": false,
54
  "normalized": false,
55
  "rstrip": false,
56
  "single_word": false,
57
- "special": true
58
  },
59
- "128007": {
60
- "content": "<|end_header_id|>",
61
  "lstrip": false,
62
  "normalized": false,
63
  "rstrip": false,
64
  "single_word": false,
65
- "special": true
66
  },
67
- "128008": {
68
- "content": "<|reserved_special_token_4|>",
69
  "lstrip": false,
70
  "normalized": false,
71
  "rstrip": false,
72
  "single_word": false,
73
- "special": true
74
  },
75
- "128009": {
76
- "content": "<|eot_id|>",
77
  "lstrip": false,
78
  "normalized": false,
79
  "rstrip": false,
80
  "single_word": false,
81
- "special": true
82
  },
83
- "128010": {
84
- "content": "<|reserved_special_token_5|>",
85
  "lstrip": false,
86
  "normalized": false,
87
  "rstrip": false,
88
  "single_word": false,
89
- "special": true
90
  },
91
- "128011": {
92
- "content": "<|reserved_special_token_6|>",
93
  "lstrip": false,
94
  "normalized": false,
95
  "rstrip": false,
96
  "single_word": false,
97
- "special": true
98
  },
99
- "128012": {
100
- "content": "<|reserved_special_token_7|>",
101
  "lstrip": false,
102
  "normalized": false,
103
  "rstrip": false,
104
  "single_word": false,
105
- "special": true
106
  },
107
- "128013": {
108
- "content": "<|reserved_special_token_8|>",
109
  "lstrip": false,
110
  "normalized": false,
111
  "rstrip": false,
112
  "single_word": false,
113
- "special": true
114
  },
115
- "128014": {
116
- "content": "<|reserved_special_token_9|>",
117
  "lstrip": false,
118
  "normalized": false,
119
  "rstrip": false,
120
  "single_word": false,
121
- "special": true
122
  },
123
- "128015": {
124
- "content": "<|reserved_special_token_10|>",
125
  "lstrip": false,
126
  "normalized": false,
127
  "rstrip": false,
128
  "single_word": false,
129
- "special": true
130
  },
131
- "128016": {
132
- "content": "<|reserved_special_token_11|>",
133
  "lstrip": false,
134
  "normalized": false,
135
  "rstrip": false,
136
  "single_word": false,
137
- "special": true
138
  },
139
- "128017": {
140
- "content": "<|reserved_special_token_12|>",
141
  "lstrip": false,
142
  "normalized": false,
143
  "rstrip": false,
144
  "single_word": false,
145
- "special": true
146
  },
147
- "128018": {
148
- "content": "<|reserved_special_token_13|>",
149
  "lstrip": false,
150
  "normalized": false,
151
  "rstrip": false,
152
  "single_word": false,
153
- "special": true
154
  },
155
- "128019": {
156
- "content": "<|reserved_special_token_14|>",
157
  "lstrip": false,
158
  "normalized": false,
159
  "rstrip": false,
160
  "single_word": false,
161
- "special": true
162
  },
163
- "128020": {
164
- "content": "<|reserved_special_token_15|>",
165
  "lstrip": false,
166
  "normalized": false,
167
  "rstrip": false,
168
  "single_word": false,
169
- "special": true
170
  },
171
- "128021": {
172
- "content": "<|reserved_special_token_16|>",
173
  "lstrip": false,
174
  "normalized": false,
175
  "rstrip": false,
176
  "single_word": false,
177
- "special": true
178
  },
179
- "128022": {
180
- "content": "<|reserved_special_token_17|>",
181
  "lstrip": false,
182
  "normalized": false,
183
  "rstrip": false,
184
  "single_word": false,
185
- "special": true
186
  },
187
- "128023": {
188
- "content": "<|reserved_special_token_18|>",
189
  "lstrip": false,
190
  "normalized": false,
191
  "rstrip": false,
192
  "single_word": false,
193
- "special": true
194
  },
195
- "128024": {
196
- "content": "<|reserved_special_token_19|>",
197
  "lstrip": false,
198
  "normalized": false,
199
  "rstrip": false,
200
  "single_word": false,
201
- "special": true
202
  },
203
- "128025": {
204
- "content": "<|reserved_special_token_20|>",
205
  "lstrip": false,
206
  "normalized": false,
207
  "rstrip": false,
208
  "single_word": false,
209
- "special": true
210
  },
211
- "128026": {
212
- "content": "<|reserved_special_token_21|>",
213
  "lstrip": false,
214
  "normalized": false,
215
  "rstrip": false,
216
  "single_word": false,
217
- "special": true
218
  },
219
- "128027": {
220
- "content": "<|reserved_special_token_22|>",
221
  "lstrip": false,
222
  "normalized": false,
223
  "rstrip": false,
224
  "single_word": false,
225
- "special": true
226
  },
227
- "128028": {
228
- "content": "<|reserved_special_token_23|>",
229
  "lstrip": false,
230
  "normalized": false,
231
  "rstrip": false,
232
  "single_word": false,
233
- "special": true
234
  },
235
- "128029": {
236
- "content": "<|reserved_special_token_24|>",
237
  "lstrip": false,
238
  "normalized": false,
239
  "rstrip": false,
240
  "single_word": false,
241
- "special": true
242
  },
243
- "128030": {
244
- "content": "<|reserved_special_token_25|>",
245
  "lstrip": false,
246
  "normalized": false,
247
  "rstrip": false,
248
  "single_word": false,
249
- "special": true
250
  },
251
- "128031": {
252
- "content": "<|reserved_special_token_26|>",
253
  "lstrip": false,
254
  "normalized": false,
255
  "rstrip": false,
256
  "single_word": false,
257
- "special": true
258
  },
259
- "128032": {
260
- "content": "<|reserved_special_token_27|>",
261
  "lstrip": false,
262
  "normalized": false,
263
  "rstrip": false,
264
  "single_word": false,
265
- "special": true
266
  },
267
- "128033": {
268
- "content": "<|reserved_special_token_28|>",
269
  "lstrip": false,
270
  "normalized": false,
271
  "rstrip": false,
272
  "single_word": false,
273
- "special": true
274
  },
275
- "128034": {
276
- "content": "<|reserved_special_token_29|>",
277
  "lstrip": false,
278
  "normalized": false,
279
  "rstrip": false,
280
  "single_word": false,
281
- "special": true
282
  },
283
- "128035": {
284
- "content": "<|reserved_special_token_30|>",
285
  "lstrip": false,
286
  "normalized": false,
287
  "rstrip": false,
288
  "single_word": false,
289
- "special": true
290
  },
291
- "128036": {
292
- "content": "<|reserved_special_token_31|>",
293
  "lstrip": false,
294
  "normalized": false,
295
  "rstrip": false,
296
  "single_word": false,
297
- "special": true
298
  },
299
- "128037": {
300
- "content": "<|reserved_special_token_32|>",
301
  "lstrip": false,
302
  "normalized": false,
303
  "rstrip": false,
304
  "single_word": false,
305
- "special": true
306
  },
307
- "128038": {
308
- "content": "<|reserved_special_token_33|>",
309
  "lstrip": false,
310
  "normalized": false,
311
  "rstrip": false,
312
  "single_word": false,
313
- "special": true
314
  },
315
- "128039": {
316
- "content": "<|reserved_special_token_34|>",
317
  "lstrip": false,
318
  "normalized": false,
319
  "rstrip": false,
320
  "single_word": false,
321
- "special": true
322
  },
323
- "128040": {
324
- "content": "<|reserved_special_token_35|>",
325
  "lstrip": false,
326
  "normalized": false,
327
  "rstrip": false,
328
  "single_word": false,
329
- "special": true
330
  },
331
- "128041": {
332
- "content": "<|reserved_special_token_36|>",
333
  "lstrip": false,
334
  "normalized": false,
335
  "rstrip": false,
336
  "single_word": false,
337
- "special": true
338
  },
339
- "128042": {
340
- "content": "<|reserved_special_token_37|>",
341
  "lstrip": false,
342
  "normalized": false,
343
  "rstrip": false,
344
  "single_word": false,
345
- "special": true
346
  },
347
- "128043": {
348
- "content": "<|reserved_special_token_38|>",
349
  "lstrip": false,
350
  "normalized": false,
351
  "rstrip": false,
352
  "single_word": false,
353
- "special": true
354
  },
355
- "128044": {
356
- "content": "<|reserved_special_token_39|>",
357
  "lstrip": false,
358
  "normalized": false,
359
  "rstrip": false,
360
  "single_word": false,
361
- "special": true
362
  },
363
- "128045": {
364
- "content": "<|reserved_special_token_40|>",
365
  "lstrip": false,
366
  "normalized": false,
367
  "rstrip": false,
368
  "single_word": false,
369
- "special": true
370
  },
371
- "128046": {
372
- "content": "<|reserved_special_token_41|>",
373
  "lstrip": false,
374
  "normalized": false,
375
  "rstrip": false,
376
  "single_word": false,
377
- "special": true
378
  },
379
- "128047": {
380
- "content": "<|reserved_special_token_42|>",
381
  "lstrip": false,
382
  "normalized": false,
383
  "rstrip": false,
384
  "single_word": false,
385
- "special": true
386
  },
387
- "128048": {
388
- "content": "<|reserved_special_token_43|>",
389
  "lstrip": false,
390
  "normalized": false,
391
  "rstrip": false,
392
  "single_word": false,
393
- "special": true
394
  },
395
- "128049": {
396
- "content": "<|reserved_special_token_44|>",
397
  "lstrip": false,
398
  "normalized": false,
399
  "rstrip": false,
400
  "single_word": false,
401
- "special": true
402
  },
403
- "128050": {
404
- "content": "<|reserved_special_token_45|>",
405
  "lstrip": false,
406
  "normalized": false,
407
  "rstrip": false,
408
  "single_word": false,
409
- "special": true
410
  },
411
- "128051": {
412
- "content": "<|reserved_special_token_46|>",
413
  "lstrip": false,
414
  "normalized": false,
415
  "rstrip": false,
416
  "single_word": false,
417
- "special": true
418
  },
419
- "128052": {
420
- "content": "<|reserved_special_token_47|>",
421
  "lstrip": false,
422
  "normalized": false,
423
  "rstrip": false,
424
  "single_word": false,
425
- "special": true
426
  },
427
- "128053": {
428
- "content": "<|reserved_special_token_48|>",
429
  "lstrip": false,
430
  "normalized": false,
431
  "rstrip": false,
432
  "single_word": false,
433
- "special": true
434
  },
435
- "128054": {
436
- "content": "<|reserved_special_token_49|>",
437
  "lstrip": false,
438
  "normalized": false,
439
  "rstrip": false,
440
  "single_word": false,
441
- "special": true
442
  },
443
- "128055": {
444
- "content": "<|reserved_special_token_50|>",
445
  "lstrip": false,
446
  "normalized": false,
447
  "rstrip": false,
448
  "single_word": false,
449
- "special": true
450
  },
451
- "128056": {
452
- "content": "<|reserved_special_token_51|>",
453
  "lstrip": false,
454
  "normalized": false,
455
  "rstrip": false,
456
  "single_word": false,
457
- "special": true
458
  },
459
- "128057": {
460
- "content": "<|reserved_special_token_52|>",
461
  "lstrip": false,
462
  "normalized": false,
463
  "rstrip": false,
464
  "single_word": false,
465
- "special": true
466
  },
467
- "128058": {
468
- "content": "<|reserved_special_token_53|>",
469
  "lstrip": false,
470
  "normalized": false,
471
  "rstrip": false,
472
  "single_word": false,
473
- "special": true
474
  },
475
- "128059": {
476
- "content": "<|reserved_special_token_54|>",
477
  "lstrip": false,
478
  "normalized": false,
479
  "rstrip": false,
480
  "single_word": false,
481
- "special": true
482
  },
483
- "128060": {
484
- "content": "<|reserved_special_token_55|>",
485
  "lstrip": false,
486
  "normalized": false,
487
  "rstrip": false,
488
  "single_word": false,
489
- "special": true
490
  },
491
- "128061": {
492
- "content": "<|reserved_special_token_56|>",
493
  "lstrip": false,
494
  "normalized": false,
495
  "rstrip": false,
496
  "single_word": false,
497
- "special": true
498
  },
499
- "128062": {
500
- "content": "<|reserved_special_token_57|>",
501
  "lstrip": false,
502
  "normalized": false,
503
  "rstrip": false,
504
  "single_word": false,
505
- "special": true
506
  },
507
- "128063": {
508
- "content": "<|reserved_special_token_58|>",
509
  "lstrip": false,
510
  "normalized": false,
511
  "rstrip": false,
512
  "single_word": false,
513
- "special": true
514
  },
515
- "128064": {
516
- "content": "<|reserved_special_token_59|>",
517
  "lstrip": false,
518
  "normalized": false,
519
  "rstrip": false,
520
  "single_word": false,
521
- "special": true
522
  },
523
- "128065": {
524
- "content": "<|reserved_special_token_60|>",
525
  "lstrip": false,
526
  "normalized": false,
527
  "rstrip": false,
528
  "single_word": false,
529
- "special": true
530
  },
531
- "128066": {
532
- "content": "<|reserved_special_token_61|>",
533
  "lstrip": false,
534
  "normalized": false,
535
  "rstrip": false,
536
  "single_word": false,
537
- "special": true
538
  },
539
- "128067": {
540
- "content": "<|reserved_special_token_62|>",
541
  "lstrip": false,
542
  "normalized": false,
543
  "rstrip": false,
544
  "single_word": false,
545
- "special": true
546
  },
547
- "128068": {
548
- "content": "<|reserved_special_token_63|>",
549
  "lstrip": false,
550
  "normalized": false,
551
  "rstrip": false,
552
  "single_word": false,
553
- "special": true
554
  },
555
- "128069": {
556
- "content": "<|reserved_special_token_64|>",
557
  "lstrip": false,
558
  "normalized": false,
559
  "rstrip": false,
560
  "single_word": false,
561
- "special": true
562
  },
563
- "128070": {
564
- "content": "<|reserved_special_token_65|>",
565
  "lstrip": false,
566
  "normalized": false,
567
  "rstrip": false,
568
  "single_word": false,
569
- "special": true
570
  },
571
- "128071": {
572
- "content": "<|reserved_special_token_66|>",
573
  "lstrip": false,
574
  "normalized": false,
575
  "rstrip": false,
576
  "single_word": false,
577
- "special": true
578
  },
579
- "128072": {
580
- "content": "<|reserved_special_token_67|>",
581
  "lstrip": false,
582
  "normalized": false,
583
  "rstrip": false,
584
  "single_word": false,
585
- "special": true
586
  },
587
- "128073": {
588
- "content": "<|reserved_special_token_68|>",
589
  "lstrip": false,
590
  "normalized": false,
591
  "rstrip": false,
592
  "single_word": false,
593
- "special": true
594
  },
595
- "128074": {
596
- "content": "<|reserved_special_token_69|>",
597
  "lstrip": false,
598
  "normalized": false,
599
  "rstrip": false,
600
  "single_word": false,
601
- "special": true
602
  },
603
- "128075": {
604
- "content": "<|reserved_special_token_70|>",
605
  "lstrip": false,
606
  "normalized": false,
607
  "rstrip": false,
608
  "single_word": false,
609
- "special": true
610
  },
611
- "128076": {
612
- "content": "<|reserved_special_token_71|>",
613
  "lstrip": false,
614
  "normalized": false,
615
  "rstrip": false,
616
  "single_word": false,
617
- "special": true
618
  },
619
- "128077": {
620
- "content": "<|reserved_special_token_72|>",
621
  "lstrip": false,
622
  "normalized": false,
623
  "rstrip": false,
624
  "single_word": false,
625
- "special": true
626
  },
627
- "128078": {
628
- "content": "<|reserved_special_token_73|>",
629
  "lstrip": false,
630
  "normalized": false,
631
  "rstrip": false,
632
  "single_word": false,
633
- "special": true
634
  },
635
- "128079": {
636
- "content": "<|reserved_special_token_74|>",
637
  "lstrip": false,
638
  "normalized": false,
639
  "rstrip": false,
640
  "single_word": false,
641
- "special": true
642
  },
643
- "128080": {
644
- "content": "<|reserved_special_token_75|>",
645
  "lstrip": false,
646
  "normalized": false,
647
  "rstrip": false,
648
  "single_word": false,
649
- "special": true
650
  },
651
- "128081": {
652
- "content": "<|reserved_special_token_76|>",
653
  "lstrip": false,
654
  "normalized": false,
655
  "rstrip": false,
656
  "single_word": false,
657
- "special": true
658
  },
659
- "128082": {
660
- "content": "<|reserved_special_token_77|>",
661
  "lstrip": false,
662
  "normalized": false,
663
  "rstrip": false,
664
  "single_word": false,
665
- "special": true
666
  },
667
- "128083": {
668
- "content": "<|reserved_special_token_78|>",
669
  "lstrip": false,
670
  "normalized": false,
671
  "rstrip": false,
672
  "single_word": false,
673
- "special": true
674
  },
675
- "128084": {
676
- "content": "<|reserved_special_token_79|>",
677
  "lstrip": false,
678
  "normalized": false,
679
  "rstrip": false,
680
  "single_word": false,
681
- "special": true
682
  },
683
- "128085": {
684
- "content": "<|reserved_special_token_80|>",
685
  "lstrip": false,
686
  "normalized": false,
687
  "rstrip": false,
688
  "single_word": false,
689
- "special": true
690
  },
691
- "128086": {
692
- "content": "<|reserved_special_token_81|>",
693
  "lstrip": false,
694
  "normalized": false,
695
  "rstrip": false,
696
  "single_word": false,
697
- "special": true
698
  },
699
- "128087": {
700
- "content": "<|reserved_special_token_82|>",
701
  "lstrip": false,
702
  "normalized": false,
703
  "rstrip": false,
704
  "single_word": false,
705
- "special": true
706
  },
707
- "128088": {
708
- "content": "<|reserved_special_token_83|>",
709
  "lstrip": false,
710
  "normalized": false,
711
  "rstrip": false,
712
  "single_word": false,
713
- "special": true
714
  },
715
- "128089": {
716
- "content": "<|reserved_special_token_84|>",
717
  "lstrip": false,
718
  "normalized": false,
719
  "rstrip": false,
720
  "single_word": false,
721
- "special": true
722
  },
723
- "128090": {
724
- "content": "<|reserved_special_token_85|>",
725
  "lstrip": false,
726
  "normalized": false,
727
  "rstrip": false,
728
  "single_word": false,
729
- "special": true
730
  },
731
- "128091": {
732
- "content": "<|reserved_special_token_86|>",
733
  "lstrip": false,
734
  "normalized": false,
735
  "rstrip": false,
736
  "single_word": false,
737
- "special": true
738
  },
739
- "128092": {
740
- "content": "<|reserved_special_token_87|>",
741
  "lstrip": false,
742
  "normalized": false,
743
  "rstrip": false,
744
  "single_word": false,
745
- "special": true
746
  },
747
- "128093": {
748
- "content": "<|reserved_special_token_88|>",
749
  "lstrip": false,
750
  "normalized": false,
751
  "rstrip": false,
752
  "single_word": false,
753
- "special": true
754
  },
755
- "128094": {
756
- "content": "<|reserved_special_token_89|>",
757
  "lstrip": false,
758
  "normalized": false,
759
  "rstrip": false,
760
  "single_word": false,
761
- "special": true
762
  },
763
- "128095": {
764
- "content": "<|reserved_special_token_90|>",
765
  "lstrip": false,
766
  "normalized": false,
767
  "rstrip": false,
768
  "single_word": false,
769
- "special": true
770
  },
771
- "128096": {
772
- "content": "<|reserved_special_token_91|>",
773
  "lstrip": false,
774
  "normalized": false,
775
  "rstrip": false,
776
  "single_word": false,
777
- "special": true
778
  },
779
- "128097": {
780
- "content": "<|reserved_special_token_92|>",
781
  "lstrip": false,
782
  "normalized": false,
783
  "rstrip": false,
784
  "single_word": false,
785
- "special": true
786
  },
787
- "128098": {
788
- "content": "<|reserved_special_token_93|>",
789
  "lstrip": false,
790
  "normalized": false,
791
  "rstrip": false,
792
  "single_word": false,
793
- "special": true
794
  },
795
- "128099": {
796
- "content": "<|reserved_special_token_94|>",
797
  "lstrip": false,
798
  "normalized": false,
799
  "rstrip": false,
800
  "single_word": false,
801
- "special": true
802
  },
803
- "128100": {
804
- "content": "<|reserved_special_token_95|>",
805
  "lstrip": false,
806
  "normalized": false,
807
  "rstrip": false,
808
  "single_word": false,
809
- "special": true
810
  },
811
- "128101": {
812
- "content": "<|reserved_special_token_96|>",
813
  "lstrip": false,
814
  "normalized": false,
815
  "rstrip": false,
816
  "single_word": false,
817
- "special": true
818
  },
819
- "128102": {
820
- "content": "<|reserved_special_token_97|>",
821
  "lstrip": false,
822
  "normalized": false,
823
  "rstrip": false,
824
  "single_word": false,
825
- "special": true
826
  },
827
- "128103": {
828
- "content": "<|reserved_special_token_98|>",
829
  "lstrip": false,
830
  "normalized": false,
831
  "rstrip": false,
832
  "single_word": false,
833
- "special": true
834
  },
835
- "128104": {
836
- "content": "<|reserved_special_token_99|>",
837
  "lstrip": false,
838
  "normalized": false,
839
  "rstrip": false,
840
  "single_word": false,
841
- "special": true
842
  },
843
- "128105": {
844
- "content": "<|reserved_special_token_100|>",
845
  "lstrip": false,
846
  "normalized": false,
847
  "rstrip": false,
848
  "single_word": false,
849
- "special": true
850
  },
851
- "128106": {
852
- "content": "<|reserved_special_token_101|>",
853
  "lstrip": false,
854
  "normalized": false,
855
  "rstrip": false,
856
  "single_word": false,
857
  "special": true
858
  },
859
- "128107": {
860
- "content": "<|reserved_special_token_102|>",
861
  "lstrip": false,
862
  "normalized": false,
863
  "rstrip": false,
864
  "single_word": false,
865
  "special": true
866
  },
867
- "128108": {
868
- "content": "<|reserved_special_token_103|>",
869
  "lstrip": false,
870
  "normalized": false,
871
  "rstrip": false,
872
  "single_word": false,
873
- "special": true
874
  },
875
- "128109": {
876
- "content": "<|reserved_special_token_104|>",
877
  "lstrip": false,
878
  "normalized": false,
879
  "rstrip": false,
880
  "single_word": false,
881
- "special": true
882
  },
883
- "128110": {
884
- "content": "<|reserved_special_token_105|>",
885
  "lstrip": false,
886
  "normalized": false,
887
  "rstrip": false,
888
  "single_word": false,
889
- "special": true
890
  },
891
- "128111": {
892
- "content": "<|reserved_special_token_106|>",
893
  "lstrip": false,
894
  "normalized": false,
895
  "rstrip": false,
896
  "single_word": false,
897
- "special": true
898
  },
899
- "128112": {
900
- "content": "<|reserved_special_token_107|>",
901
  "lstrip": false,
902
  "normalized": false,
903
  "rstrip": false,
904
  "single_word": false,
905
- "special": true
906
  },
907
- "128113": {
908
- "content": "<|reserved_special_token_108|>",
909
  "lstrip": false,
910
  "normalized": false,
911
  "rstrip": false,
912
  "single_word": false,
913
- "special": true
914
  },
915
- "128114": {
916
- "content": "<|reserved_special_token_109|>",
917
  "lstrip": false,
918
  "normalized": false,
919
  "rstrip": false,
920
  "single_word": false,
921
- "special": true
922
  },
923
- "128115": {
924
- "content": "<|reserved_special_token_110|>",
925
  "lstrip": false,
926
  "normalized": false,
927
  "rstrip": false,
928
  "single_word": false,
929
- "special": true
930
  },
931
- "128116": {
932
- "content": "<|reserved_special_token_111|>",
933
  "lstrip": false,
934
  "normalized": false,
935
  "rstrip": false,
936
  "single_word": false,
937
- "special": true
938
  },
939
- "128117": {
940
- "content": "<|reserved_special_token_112|>",
941
  "lstrip": false,
942
  "normalized": false,
943
  "rstrip": false,
944
  "single_word": false,
945
- "special": true
946
  },
947
- "128118": {
948
- "content": "<|reserved_special_token_113|>",
949
  "lstrip": false,
950
  "normalized": false,
951
  "rstrip": false,
952
  "single_word": false,
953
- "special": true
954
  },
955
- "128119": {
956
- "content": "<|reserved_special_token_114|>",
957
  "lstrip": false,
958
  "normalized": false,
959
  "rstrip": false,
960
  "single_word": false,
961
- "special": true
962
  },
963
- "128120": {
964
- "content": "<|reserved_special_token_115|>",
965
  "lstrip": false,
966
  "normalized": false,
967
  "rstrip": false,
968
  "single_word": false,
969
- "special": true
970
  },
971
- "128121": {
972
- "content": "<|reserved_special_token_116|>",
973
  "lstrip": false,
974
  "normalized": false,
975
  "rstrip": false,
976
  "single_word": false,
977
- "special": true
978
  },
979
- "128122": {
980
- "content": "<|reserved_special_token_117|>",
981
  "lstrip": false,
982
  "normalized": false,
983
  "rstrip": false,
984
  "single_word": false,
985
- "special": true
986
  },
987
- "128123": {
988
- "content": "<|reserved_special_token_118|>",
989
  "lstrip": false,
990
  "normalized": false,
991
  "rstrip": false,
992
  "single_word": false,
993
- "special": true
994
  },
995
- "128124": {
996
- "content": "<|reserved_special_token_119|>",
997
  "lstrip": false,
998
  "normalized": false,
999
  "rstrip": false,
1000
  "single_word": false,
1001
- "special": true
1002
  },
1003
- "128125": {
1004
- "content": "<|reserved_special_token_120|>",
1005
  "lstrip": false,
1006
  "normalized": false,
1007
  "rstrip": false,
1008
  "single_word": false,
1009
- "special": true
1010
  },
1011
- "128126": {
1012
- "content": "<|reserved_special_token_121|>",
1013
  "lstrip": false,
1014
  "normalized": false,
1015
  "rstrip": false,
1016
  "single_word": false,
1017
- "special": true
1018
  },
1019
- "128127": {
1020
- "content": "<|reserved_special_token_122|>",
1021
  "lstrip": false,
1022
  "normalized": false,
1023
  "rstrip": false,
1024
  "single_word": false,
1025
- "special": true
1026
  },
1027
- "128128": {
1028
- "content": "<|reserved_special_token_123|>",
1029
  "lstrip": false,
1030
  "normalized": false,
1031
  "rstrip": false,
1032
  "single_word": false,
1033
- "special": true
1034
  },
1035
- "128129": {
1036
- "content": "<|reserved_special_token_124|>",
1037
  "lstrip": false,
1038
  "normalized": false,
1039
  "rstrip": false,
1040
  "single_word": false,
1041
- "special": true
1042
  },
1043
- "128130": {
1044
- "content": "<|reserved_special_token_125|>",
1045
  "lstrip": false,
1046
  "normalized": false,
1047
  "rstrip": false,
1048
  "single_word": false,
1049
- "special": true
1050
  },
1051
- "128131": {
1052
- "content": "<|reserved_special_token_126|>",
1053
  "lstrip": false,
1054
  "normalized": false,
1055
  "rstrip": false,
1056
  "single_word": false,
1057
- "special": true
1058
  },
1059
- "128132": {
1060
- "content": "<|reserved_special_token_127|>",
1061
  "lstrip": false,
1062
  "normalized": false,
1063
  "rstrip": false,
1064
  "single_word": false,
1065
- "special": true
1066
  },
1067
- "128133": {
1068
- "content": "<|reserved_special_token_128|>",
1069
  "lstrip": false,
1070
  "normalized": false,
1071
  "rstrip": false,
1072
  "single_word": false,
1073
- "special": true
1074
  },
1075
- "128134": {
1076
- "content": "<|reserved_special_token_129|>",
1077
  "lstrip": false,
1078
  "normalized": false,
1079
  "rstrip": false,
1080
  "single_word": false,
1081
- "special": true
1082
  },
1083
- "128135": {
1084
- "content": "<|reserved_special_token_130|>",
1085
  "lstrip": false,
1086
  "normalized": false,
1087
  "rstrip": false,
1088
  "single_word": false,
1089
- "special": true
1090
  },
1091
- "128136": {
1092
- "content": "<|reserved_special_token_131|>",
1093
  "lstrip": false,
1094
  "normalized": false,
1095
  "rstrip": false,
1096
  "single_word": false,
1097
- "special": true
1098
  },
1099
- "128137": {
1100
- "content": "<|reserved_special_token_132|>",
1101
  "lstrip": false,
1102
  "normalized": false,
1103
  "rstrip": false,
1104
  "single_word": false,
1105
- "special": true
1106
  },
1107
- "128138": {
1108
- "content": "<|reserved_special_token_133|>",
1109
  "lstrip": false,
1110
  "normalized": false,
1111
  "rstrip": false,
1112
  "single_word": false,
1113
- "special": true
1114
  },
1115
- "128139": {
1116
- "content": "<|reserved_special_token_134|>",
1117
  "lstrip": false,
1118
  "normalized": false,
1119
  "rstrip": false,
1120
  "single_word": false,
1121
- "special": true
1122
  },
1123
- "128140": {
1124
- "content": "<|reserved_special_token_135|>",
1125
  "lstrip": false,
1126
  "normalized": false,
1127
  "rstrip": false,
1128
  "single_word": false,
1129
- "special": true
1130
  },
1131
- "128141": {
1132
- "content": "<|reserved_special_token_136|>",
1133
  "lstrip": false,
1134
  "normalized": false,
1135
  "rstrip": false,
1136
  "single_word": false,
1137
- "special": true
1138
  },
1139
- "128142": {
1140
- "content": "<|reserved_special_token_137|>",
1141
  "lstrip": false,
1142
  "normalized": false,
1143
  "rstrip": false,
1144
  "single_word": false,
1145
- "special": true
1146
  },
1147
- "128143": {
1148
- "content": "<|reserved_special_token_138|>",
1149
  "lstrip": false,
1150
  "normalized": false,
1151
  "rstrip": false,
1152
  "single_word": false,
1153
- "special": true
1154
  },
1155
- "128144": {
1156
- "content": "<|reserved_special_token_139|>",
1157
  "lstrip": false,
1158
  "normalized": false,
1159
  "rstrip": false,
1160
  "single_word": false,
1161
- "special": true
1162
  },
1163
- "128145": {
1164
- "content": "<|reserved_special_token_140|>",
1165
  "lstrip": false,
1166
  "normalized": false,
1167
  "rstrip": false,
1168
  "single_word": false,
1169
- "special": true
1170
  },
1171
- "128146": {
1172
- "content": "<|reserved_special_token_141|>",
1173
  "lstrip": false,
1174
  "normalized": false,
1175
  "rstrip": false,
1176
  "single_word": false,
1177
- "special": true
1178
  },
1179
- "128147": {
1180
- "content": "<|reserved_special_token_142|>",
1181
  "lstrip": false,
1182
  "normalized": false,
1183
  "rstrip": false,
1184
  "single_word": false,
1185
- "special": true
1186
  },
1187
- "128148": {
1188
- "content": "<|reserved_special_token_143|>",
1189
  "lstrip": false,
1190
  "normalized": false,
1191
  "rstrip": false,
1192
  "single_word": false,
1193
- "special": true
1194
  },
1195
- "128149": {
1196
- "content": "<|reserved_special_token_144|>",
1197
  "lstrip": false,
1198
  "normalized": false,
1199
  "rstrip": false,
1200
  "single_word": false,
1201
- "special": true
1202
  },
1203
- "128150": {
1204
- "content": "<|reserved_special_token_145|>",
1205
  "lstrip": false,
1206
  "normalized": false,
1207
  "rstrip": false,
1208
  "single_word": false,
1209
- "special": true
1210
  },
1211
- "128151": {
1212
- "content": "<|reserved_special_token_146|>",
1213
  "lstrip": false,
1214
  "normalized": false,
1215
  "rstrip": false,
1216
  "single_word": false,
1217
- "special": true
1218
  },
1219
- "128152": {
1220
- "content": "<|reserved_special_token_147|>",
1221
  "lstrip": false,
1222
  "normalized": false,
1223
  "rstrip": false,
1224
  "single_word": false,
1225
- "special": true
1226
  },
1227
- "128153": {
1228
- "content": "<|reserved_special_token_148|>",
1229
  "lstrip": false,
1230
  "normalized": false,
1231
  "rstrip": false,
1232
  "single_word": false,
1233
- "special": true
1234
  },
1235
- "128154": {
1236
- "content": "<|reserved_special_token_149|>",
1237
  "lstrip": false,
1238
  "normalized": false,
1239
  "rstrip": false,
1240
  "single_word": false,
1241
- "special": true
1242
  },
1243
- "128155": {
1244
- "content": "<|reserved_special_token_150|>",
1245
  "lstrip": false,
1246
  "normalized": false,
1247
  "rstrip": false,
1248
  "single_word": false,
1249
- "special": true
1250
  },
1251
- "128156": {
1252
- "content": "<|reserved_special_token_151|>",
1253
  "lstrip": false,
1254
  "normalized": false,
1255
  "rstrip": false,
1256
  "single_word": false,
1257
- "special": true
1258
  },
1259
- "128157": {
1260
- "content": "<|reserved_special_token_152|>",
1261
  "lstrip": false,
1262
  "normalized": false,
1263
  "rstrip": false,
1264
  "single_word": false,
1265
- "special": true
1266
  },
1267
- "128158": {
1268
- "content": "<|reserved_special_token_153|>",
1269
  "lstrip": false,
1270
  "normalized": false,
1271
  "rstrip": false,
1272
  "single_word": false,
1273
- "special": true
1274
  },
1275
- "128159": {
1276
- "content": "<|reserved_special_token_154|>",
1277
  "lstrip": false,
1278
  "normalized": false,
1279
  "rstrip": false,
1280
  "single_word": false,
1281
- "special": true
1282
  },
1283
- "128160": {
1284
- "content": "<|reserved_special_token_155|>",
1285
  "lstrip": false,
1286
  "normalized": false,
1287
  "rstrip": false,
1288
  "single_word": false,
1289
- "special": true
1290
  },
1291
- "128161": {
1292
- "content": "<|reserved_special_token_156|>",
1293
  "lstrip": false,
1294
  "normalized": false,
1295
  "rstrip": false,
1296
  "single_word": false,
1297
- "special": true
1298
  },
1299
- "128162": {
1300
- "content": "<|reserved_special_token_157|>",
1301
  "lstrip": false,
1302
  "normalized": false,
1303
  "rstrip": false,
1304
  "single_word": false,
1305
- "special": true
1306
  },
1307
- "128163": {
1308
- "content": "<|reserved_special_token_158|>",
1309
  "lstrip": false,
1310
  "normalized": false,
1311
  "rstrip": false,
1312
  "single_word": false,
1313
- "special": true
1314
  },
1315
- "128164": {
1316
- "content": "<|reserved_special_token_159|>",
1317
  "lstrip": false,
1318
  "normalized": false,
1319
  "rstrip": false,
1320
  "single_word": false,
1321
- "special": true
1322
  },
1323
- "128165": {
1324
- "content": "<|reserved_special_token_160|>",
1325
  "lstrip": false,
1326
  "normalized": false,
1327
  "rstrip": false,
1328
  "single_word": false,
1329
- "special": true
1330
  },
1331
- "128166": {
1332
- "content": "<|reserved_special_token_161|>",
1333
  "lstrip": false,
1334
  "normalized": false,
1335
  "rstrip": false,
1336
  "single_word": false,
1337
- "special": true
1338
  },
1339
- "128167": {
1340
- "content": "<|reserved_special_token_162|>",
1341
  "lstrip": false,
1342
  "normalized": false,
1343
  "rstrip": false,
1344
  "single_word": false,
1345
- "special": true
1346
  },
1347
- "128168": {
1348
- "content": "<|reserved_special_token_163|>",
1349
  "lstrip": false,
1350
  "normalized": false,
1351
  "rstrip": false,
1352
  "single_word": false,
1353
- "special": true
1354
  },
1355
- "128169": {
1356
- "content": "<|reserved_special_token_164|>",
1357
  "lstrip": false,
1358
  "normalized": false,
1359
  "rstrip": false,
1360
  "single_word": false,
1361
- "special": true
1362
  },
1363
- "128170": {
1364
- "content": "<|reserved_special_token_165|>",
1365
  "lstrip": false,
1366
  "normalized": false,
1367
  "rstrip": false,
1368
  "single_word": false,
1369
- "special": true
1370
  },
1371
- "128171": {
1372
- "content": "<|reserved_special_token_166|>",
1373
  "lstrip": false,
1374
  "normalized": false,
1375
  "rstrip": false,
1376
  "single_word": false,
1377
- "special": true
1378
  },
1379
- "128172": {
1380
- "content": "<|reserved_special_token_167|>",
1381
  "lstrip": false,
1382
  "normalized": false,
1383
  "rstrip": false,
1384
  "single_word": false,
1385
- "special": true
1386
  },
1387
- "128173": {
1388
- "content": "<|reserved_special_token_168|>",
1389
  "lstrip": false,
1390
  "normalized": false,
1391
  "rstrip": false,
1392
  "single_word": false,
1393
- "special": true
1394
  },
1395
- "128174": {
1396
- "content": "<|reserved_special_token_169|>",
1397
  "lstrip": false,
1398
  "normalized": false,
1399
  "rstrip": false,
1400
  "single_word": false,
1401
- "special": true
1402
  },
1403
- "128175": {
1404
- "content": "<|reserved_special_token_170|>",
1405
  "lstrip": false,
1406
  "normalized": false,
1407
  "rstrip": false,
1408
  "single_word": false,
1409
- "special": true
1410
  },
1411
- "128176": {
1412
- "content": "<|reserved_special_token_171|>",
1413
  "lstrip": false,
1414
  "normalized": false,
1415
  "rstrip": false,
1416
  "single_word": false,
1417
- "special": true
1418
  },
1419
- "128177": {
1420
- "content": "<|reserved_special_token_172|>",
1421
  "lstrip": false,
1422
  "normalized": false,
1423
  "rstrip": false,
1424
  "single_word": false,
1425
- "special": true
1426
  },
1427
- "128178": {
1428
- "content": "<|reserved_special_token_173|>",
1429
  "lstrip": false,
1430
  "normalized": false,
1431
  "rstrip": false,
1432
  "single_word": false,
1433
- "special": true
1434
  },
1435
- "128179": {
1436
- "content": "<|reserved_special_token_174|>",
1437
  "lstrip": false,
1438
  "normalized": false,
1439
  "rstrip": false,
1440
  "single_word": false,
1441
- "special": true
1442
  },
1443
- "128180": {
1444
- "content": "<|reserved_special_token_175|>",
1445
  "lstrip": false,
1446
  "normalized": false,
1447
  "rstrip": false,
1448
  "single_word": false,
1449
- "special": true
1450
  },
1451
- "128181": {
1452
- "content": "<|reserved_special_token_176|>",
1453
  "lstrip": false,
1454
  "normalized": false,
1455
  "rstrip": false,
1456
  "single_word": false,
1457
- "special": true
1458
  },
1459
- "128182": {
1460
- "content": "<|reserved_special_token_177|>",
1461
  "lstrip": false,
1462
  "normalized": false,
1463
  "rstrip": false,
1464
  "single_word": false,
1465
- "special": true
1466
  },
1467
- "128183": {
1468
- "content": "<|reserved_special_token_178|>",
1469
  "lstrip": false,
1470
  "normalized": false,
1471
  "rstrip": false,
1472
  "single_word": false,
1473
- "special": true
1474
  },
1475
- "128184": {
1476
- "content": "<|reserved_special_token_179|>",
1477
  "lstrip": false,
1478
  "normalized": false,
1479
  "rstrip": false,
1480
  "single_word": false,
1481
- "special": true
1482
  },
1483
- "128185": {
1484
- "content": "<|reserved_special_token_180|>",
1485
  "lstrip": false,
1486
  "normalized": false,
1487
  "rstrip": false,
1488
  "single_word": false,
1489
- "special": true
1490
  },
1491
- "128186": {
1492
- "content": "<|reserved_special_token_181|>",
1493
  "lstrip": false,
1494
  "normalized": false,
1495
  "rstrip": false,
1496
  "single_word": false,
1497
- "special": true
1498
  },
1499
- "128187": {
1500
- "content": "<|reserved_special_token_182|>",
1501
  "lstrip": false,
1502
  "normalized": false,
1503
  "rstrip": false,
1504
  "single_word": false,
1505
- "special": true
1506
  },
1507
- "128188": {
1508
- "content": "<|reserved_special_token_183|>",
1509
  "lstrip": false,
1510
  "normalized": false,
1511
  "rstrip": false,
1512
  "single_word": false,
1513
- "special": true
1514
  },
1515
- "128189": {
1516
- "content": "<|reserved_special_token_184|>",
1517
  "lstrip": false,
1518
  "normalized": false,
1519
  "rstrip": false,
1520
  "single_word": false,
1521
- "special": true
1522
  },
1523
- "128190": {
1524
- "content": "<|reserved_special_token_185|>",
1525
  "lstrip": false,
1526
  "normalized": false,
1527
  "rstrip": false,
1528
  "single_word": false,
1529
- "special": true
1530
  },
1531
- "128191": {
1532
- "content": "<|reserved_special_token_186|>",
1533
  "lstrip": false,
1534
  "normalized": false,
1535
  "rstrip": false,
1536
  "single_word": false,
1537
- "special": true
1538
  },
1539
- "128192": {
1540
- "content": "<|reserved_special_token_187|>",
1541
  "lstrip": false,
1542
  "normalized": false,
1543
  "rstrip": false,
1544
  "single_word": false,
1545
- "special": true
1546
  },
1547
- "128193": {
1548
- "content": "<|reserved_special_token_188|>",
1549
  "lstrip": false,
1550
  "normalized": false,
1551
  "rstrip": false,
1552
  "single_word": false,
1553
- "special": true
1554
  },
1555
- "128194": {
1556
- "content": "<|reserved_special_token_189|>",
1557
  "lstrip": false,
1558
  "normalized": false,
1559
  "rstrip": false,
1560
  "single_word": false,
1561
- "special": true
1562
  },
1563
- "128195": {
1564
- "content": "<|reserved_special_token_190|>",
1565
  "lstrip": false,
1566
  "normalized": false,
1567
  "rstrip": false,
1568
  "single_word": false,
1569
- "special": true
1570
  },
1571
- "128196": {
1572
- "content": "<|reserved_special_token_191|>",
1573
  "lstrip": false,
1574
  "normalized": false,
1575
  "rstrip": false,
1576
  "single_word": false,
1577
- "special": true
1578
  },
1579
- "128197": {
1580
- "content": "<|reserved_special_token_192|>",
1581
  "lstrip": false,
1582
  "normalized": false,
1583
  "rstrip": false,
1584
  "single_word": false,
1585
- "special": true
1586
  },
1587
- "128198": {
1588
- "content": "<|reserved_special_token_193|>",
1589
  "lstrip": false,
1590
  "normalized": false,
1591
  "rstrip": false,
1592
  "single_word": false,
1593
- "special": true
1594
  },
1595
- "128199": {
1596
- "content": "<|reserved_special_token_194|>",
1597
  "lstrip": false,
1598
  "normalized": false,
1599
  "rstrip": false,
1600
  "single_word": false,
1601
- "special": true
1602
  },
1603
- "128200": {
1604
- "content": "<|reserved_special_token_195|>",
1605
  "lstrip": false,
1606
  "normalized": false,
1607
  "rstrip": false,
1608
  "single_word": false,
1609
- "special": true
1610
  },
1611
- "128201": {
1612
- "content": "<|reserved_special_token_196|>",
1613
  "lstrip": false,
1614
  "normalized": false,
1615
  "rstrip": false,
1616
  "single_word": false,
1617
- "special": true
1618
  },
1619
- "128202": {
1620
- "content": "<|reserved_special_token_197|>",
1621
  "lstrip": false,
1622
  "normalized": false,
1623
  "rstrip": false,
1624
  "single_word": false,
1625
- "special": true
1626
  },
1627
- "128203": {
1628
- "content": "<|reserved_special_token_198|>",
1629
  "lstrip": false,
1630
  "normalized": false,
1631
  "rstrip": false,
1632
  "single_word": false,
1633
- "special": true
1634
  },
1635
- "128204": {
1636
- "content": "<|reserved_special_token_199|>",
1637
  "lstrip": false,
1638
  "normalized": false,
1639
  "rstrip": false,
1640
  "single_word": false,
1641
- "special": true
1642
  },
1643
- "128205": {
1644
- "content": "<|reserved_special_token_200|>",
1645
  "lstrip": false,
1646
  "normalized": false,
1647
  "rstrip": false,
1648
  "single_word": false,
1649
- "special": true
1650
  },
1651
- "128206": {
1652
- "content": "<|reserved_special_token_201|>",
1653
  "lstrip": false,
1654
  "normalized": false,
1655
  "rstrip": false,
1656
  "single_word": false,
1657
- "special": true
1658
  },
1659
- "128207": {
1660
- "content": "<|reserved_special_token_202|>",
1661
  "lstrip": false,
1662
  "normalized": false,
1663
  "rstrip": false,
1664
  "single_word": false,
1665
- "special": true
1666
  },
1667
- "128208": {
1668
- "content": "<|reserved_special_token_203|>",
1669
  "lstrip": false,
1670
  "normalized": false,
1671
  "rstrip": false,
1672
  "single_word": false,
1673
- "special": true
1674
  },
1675
- "128209": {
1676
- "content": "<|reserved_special_token_204|>",
1677
  "lstrip": false,
1678
  "normalized": false,
1679
  "rstrip": false,
1680
  "single_word": false,
1681
- "special": true
1682
  },
1683
- "128210": {
1684
- "content": "<|reserved_special_token_205|>",
1685
  "lstrip": false,
1686
  "normalized": false,
1687
  "rstrip": false,
1688
  "single_word": false,
1689
- "special": true
1690
  },
1691
- "128211": {
1692
- "content": "<|reserved_special_token_206|>",
1693
  "lstrip": false,
1694
  "normalized": false,
1695
  "rstrip": false,
1696
  "single_word": false,
1697
- "special": true
1698
  },
1699
- "128212": {
1700
- "content": "<|reserved_special_token_207|>",
1701
  "lstrip": false,
1702
  "normalized": false,
1703
  "rstrip": false,
1704
  "single_word": false,
1705
- "special": true
1706
  },
1707
- "128213": {
1708
- "content": "<|reserved_special_token_208|>",
1709
  "lstrip": false,
1710
  "normalized": false,
1711
  "rstrip": false,
1712
  "single_word": false,
1713
- "special": true
1714
  },
1715
- "128214": {
1716
- "content": "<|reserved_special_token_209|>",
1717
  "lstrip": false,
1718
  "normalized": false,
1719
  "rstrip": false,
1720
  "single_word": false,
1721
- "special": true
1722
  },
1723
- "128215": {
1724
- "content": "<|reserved_special_token_210|>",
1725
  "lstrip": false,
1726
  "normalized": false,
1727
  "rstrip": false,
1728
  "single_word": false,
1729
- "special": true
1730
  },
1731
- "128216": {
1732
- "content": "<|reserved_special_token_211|>",
1733
  "lstrip": false,
1734
  "normalized": false,
1735
  "rstrip": false,
1736
  "single_word": false,
1737
- "special": true
1738
- },
1739
- "128217": {
1740
- "content": "<|reserved_special_token_212|>",
1741
- "lstrip": false,
1742
- "normalized": false,
1743
- "rstrip": false,
1744
- "single_word": false,
1745
- "special": true
1746
- },
1747
- "128218": {
1748
- "content": "<|reserved_special_token_213|>",
1749
- "lstrip": false,
1750
- "normalized": false,
1751
- "rstrip": false,
1752
- "single_word": false,
1753
- "special": true
1754
- },
1755
- "128219": {
1756
- "content": "<|reserved_special_token_214|>",
1757
- "lstrip": false,
1758
- "normalized": false,
1759
- "rstrip": false,
1760
- "single_word": false,
1761
- "special": true
1762
- },
1763
- "128220": {
1764
- "content": "<|reserved_special_token_215|>",
1765
- "lstrip": false,
1766
- "normalized": false,
1767
- "rstrip": false,
1768
- "single_word": false,
1769
- "special": true
1770
- },
1771
- "128221": {
1772
- "content": "<|reserved_special_token_216|>",
1773
- "lstrip": false,
1774
- "normalized": false,
1775
- "rstrip": false,
1776
- "single_word": false,
1777
- "special": true
1778
- },
1779
- "128222": {
1780
- "content": "<|reserved_special_token_217|>",
1781
- "lstrip": false,
1782
- "normalized": false,
1783
- "rstrip": false,
1784
- "single_word": false,
1785
- "special": true
1786
- },
1787
- "128223": {
1788
- "content": "<|reserved_special_token_218|>",
1789
- "lstrip": false,
1790
- "normalized": false,
1791
- "rstrip": false,
1792
- "single_word": false,
1793
- "special": true
1794
- },
1795
- "128224": {
1796
- "content": "<|reserved_special_token_219|>",
1797
- "lstrip": false,
1798
- "normalized": false,
1799
- "rstrip": false,
1800
- "single_word": false,
1801
- "special": true
1802
- },
1803
- "128225": {
1804
- "content": "<|reserved_special_token_220|>",
1805
- "lstrip": false,
1806
- "normalized": false,
1807
- "rstrip": false,
1808
- "single_word": false,
1809
- "special": true
1810
- },
1811
- "128226": {
1812
- "content": "<|reserved_special_token_221|>",
1813
- "lstrip": false,
1814
- "normalized": false,
1815
- "rstrip": false,
1816
- "single_word": false,
1817
- "special": true
1818
- },
1819
- "128227": {
1820
- "content": "<|reserved_special_token_222|>",
1821
- "lstrip": false,
1822
- "normalized": false,
1823
- "rstrip": false,
1824
- "single_word": false,
1825
- "special": true
1826
- },
1827
- "128228": {
1828
- "content": "<|reserved_special_token_223|>",
1829
- "lstrip": false,
1830
- "normalized": false,
1831
- "rstrip": false,
1832
- "single_word": false,
1833
- "special": true
1834
- },
1835
- "128229": {
1836
- "content": "<|reserved_special_token_224|>",
1837
- "lstrip": false,
1838
- "normalized": false,
1839
- "rstrip": false,
1840
- "single_word": false,
1841
- "special": true
1842
- },
1843
- "128230": {
1844
- "content": "<|reserved_special_token_225|>",
1845
- "lstrip": false,
1846
- "normalized": false,
1847
- "rstrip": false,
1848
- "single_word": false,
1849
- "special": true
1850
- },
1851
- "128231": {
1852
- "content": "<|reserved_special_token_226|>",
1853
- "lstrip": false,
1854
- "normalized": false,
1855
- "rstrip": false,
1856
- "single_word": false,
1857
- "special": true
1858
- },
1859
- "128232": {
1860
- "content": "<|reserved_special_token_227|>",
1861
- "lstrip": false,
1862
- "normalized": false,
1863
- "rstrip": false,
1864
- "single_word": false,
1865
- "special": true
1866
- },
1867
- "128233": {
1868
- "content": "<|reserved_special_token_228|>",
1869
- "lstrip": false,
1870
- "normalized": false,
1871
- "rstrip": false,
1872
- "single_word": false,
1873
- "special": true
1874
- },
1875
- "128234": {
1876
- "content": "<|reserved_special_token_229|>",
1877
- "lstrip": false,
1878
- "normalized": false,
1879
- "rstrip": false,
1880
- "single_word": false,
1881
- "special": true
1882
- },
1883
- "128235": {
1884
- "content": "<|reserved_special_token_230|>",
1885
- "lstrip": false,
1886
- "normalized": false,
1887
- "rstrip": false,
1888
- "single_word": false,
1889
- "special": true
1890
- },
1891
- "128236": {
1892
- "content": "<|reserved_special_token_231|>",
1893
- "lstrip": false,
1894
- "normalized": false,
1895
- "rstrip": false,
1896
- "single_word": false,
1897
- "special": true
1898
- },
1899
- "128237": {
1900
- "content": "<|reserved_special_token_232|>",
1901
- "lstrip": false,
1902
- "normalized": false,
1903
- "rstrip": false,
1904
- "single_word": false,
1905
- "special": true
1906
- },
1907
- "128238": {
1908
- "content": "<|reserved_special_token_233|>",
1909
- "lstrip": false,
1910
- "normalized": false,
1911
- "rstrip": false,
1912
- "single_word": false,
1913
- "special": true
1914
- },
1915
- "128239": {
1916
- "content": "<|reserved_special_token_234|>",
1917
- "lstrip": false,
1918
- "normalized": false,
1919
- "rstrip": false,
1920
- "single_word": false,
1921
- "special": true
1922
- },
1923
- "128240": {
1924
- "content": "<|reserved_special_token_235|>",
1925
- "lstrip": false,
1926
- "normalized": false,
1927
- "rstrip": false,
1928
- "single_word": false,
1929
- "special": true
1930
- },
1931
- "128241": {
1932
- "content": "<|reserved_special_token_236|>",
1933
- "lstrip": false,
1934
- "normalized": false,
1935
- "rstrip": false,
1936
- "single_word": false,
1937
- "special": true
1938
- },
1939
- "128242": {
1940
- "content": "<|reserved_special_token_237|>",
1941
- "lstrip": false,
1942
- "normalized": false,
1943
- "rstrip": false,
1944
- "single_word": false,
1945
- "special": true
1946
- },
1947
- "128243": {
1948
- "content": "<|reserved_special_token_238|>",
1949
- "lstrip": false,
1950
- "normalized": false,
1951
- "rstrip": false,
1952
- "single_word": false,
1953
- "special": true
1954
- },
1955
- "128244": {
1956
- "content": "<|reserved_special_token_239|>",
1957
- "lstrip": false,
1958
- "normalized": false,
1959
- "rstrip": false,
1960
- "single_word": false,
1961
- "special": true
1962
- },
1963
- "128245": {
1964
- "content": "<|reserved_special_token_240|>",
1965
- "lstrip": false,
1966
- "normalized": false,
1967
- "rstrip": false,
1968
- "single_word": false,
1969
- "special": true
1970
- },
1971
- "128246": {
1972
- "content": "<|reserved_special_token_241|>",
1973
- "lstrip": false,
1974
- "normalized": false,
1975
- "rstrip": false,
1976
- "single_word": false,
1977
- "special": true
1978
- },
1979
- "128247": {
1980
- "content": "<|reserved_special_token_242|>",
1981
- "lstrip": false,
1982
- "normalized": false,
1983
- "rstrip": false,
1984
- "single_word": false,
1985
- "special": true
1986
- },
1987
- "128248": {
1988
- "content": "<|reserved_special_token_243|>",
1989
- "lstrip": false,
1990
- "normalized": false,
1991
- "rstrip": false,
1992
- "single_word": false,
1993
- "special": true
1994
- },
1995
- "128249": {
1996
- "content": "<|reserved_special_token_244|>",
1997
- "lstrip": false,
1998
- "normalized": false,
1999
- "rstrip": false,
2000
- "single_word": false,
2001
- "special": true
2002
- },
2003
- "128250": {
2004
- "content": "<|reserved_special_token_245|>",
2005
- "lstrip": false,
2006
- "normalized": false,
2007
- "rstrip": false,
2008
- "single_word": false,
2009
- "special": true
2010
- },
2011
- "128251": {
2012
- "content": "<|reserved_special_token_246|>",
2013
- "lstrip": false,
2014
- "normalized": false,
2015
- "rstrip": false,
2016
- "single_word": false,
2017
- "special": true
2018
- },
2019
- "128252": {
2020
- "content": "<|reserved_special_token_247|>",
2021
- "lstrip": false,
2022
- "normalized": false,
2023
- "rstrip": false,
2024
- "single_word": false,
2025
- "special": true
2026
- },
2027
- "128253": {
2028
- "content": "<|reserved_special_token_248|>",
2029
- "lstrip": false,
2030
- "normalized": false,
2031
- "rstrip": false,
2032
- "single_word": false,
2033
- "special": true
2034
- },
2035
- "128254": {
2036
- "content": "<|reserved_special_token_249|>",
2037
- "lstrip": false,
2038
- "normalized": false,
2039
- "rstrip": false,
2040
- "single_word": false,
2041
- "special": true
2042
- },
2043
- "128255": {
2044
- "content": "<|reserved_special_token_250|>",
2045
- "lstrip": false,
2046
- "normalized": false,
2047
- "rstrip": false,
2048
- "single_word": false,
2049
- "special": true
2050
  }
2051
  },
2052
- "bos_token": "<|begin_of_text|>",
2053
- "clean_up_tokenization_spaces": true,
2054
- "eos_token": "<|end_of_text|>",
2055
- "model_input_names": [
2056
- "input_ids",
2057
- "attention_mask"
2058
  ],
 
 
 
 
2059
  "model_max_length": 8192,
2060
- "pad_token": "<|end_of_text|>",
2061
  "padding_side": "left",
2062
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
 
2063
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
  "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
  "lstrip": false,
8
  "normalized": false,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
12
  },
13
+ "1": {
14
+ "content": "<eos>",
15
  "lstrip": false,
16
  "normalized": false,
17
  "rstrip": false,
18
  "single_word": false,
19
  "special": true
20
  },
21
+ "2": {
22
+ "content": "<bos>",
23
  "lstrip": false,
24
  "normalized": false,
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
  },
29
+ "3": {
30
+ "content": "<unk>",
31
  "lstrip": false,
32
  "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
  },
37
+ "4": {
38
+ "content": "<mask>",
39
  "lstrip": false,
40
  "normalized": false,
41
  "rstrip": false,
42
  "single_word": false,
43
+ "special": false
44
  },
45
+ "5": {
46
+ "content": "<2mass>",
47
  "lstrip": false,
48
  "normalized": false,
49
  "rstrip": false,
50
  "single_word": false,
51
+ "special": false
52
  },
53
+ "6": {
54
+ "content": "[@BOS@]",
55
  "lstrip": false,
56
  "normalized": false,
57
  "rstrip": false,
58
  "single_word": false,
59
+ "special": false
60
  },
61
+ "7": {
62
+ "content": "<unused0>",
63
  "lstrip": false,
64
  "normalized": false,
65
  "rstrip": false,
66
  "single_word": false,
67
+ "special": false
68
  },
69
+ "8": {
70
+ "content": "<unused1>",
71
  "lstrip": false,
72
  "normalized": false,
73
  "rstrip": false,
74
  "single_word": false,
75
+ "special": false
76
  },
77
+ "9": {
78
+ "content": "<unused2>",
79
  "lstrip": false,
80
  "normalized": false,
81
  "rstrip": false,
82
  "single_word": false,
83
+ "special": false
84
  },
85
+ "10": {
86
+ "content": "<unused3>",
87
  "lstrip": false,
88
  "normalized": false,
89
  "rstrip": false,
90
  "single_word": false,
91
+ "special": false
92
  },
93
+ "11": {
94
+ "content": "<unused4>",
95
  "lstrip": false,
96
  "normalized": false,
97
  "rstrip": false,
98
  "single_word": false,
99
+ "special": false
100
  },
101
+ "12": {
102
+ "content": "<unused5>",
103
  "lstrip": false,
104
  "normalized": false,
105
  "rstrip": false,
106
  "single_word": false,
107
+ "special": false
108
  },
109
+ "13": {
110
+ "content": "<unused6>",
111
  "lstrip": false,
112
  "normalized": false,
113
  "rstrip": false,
114
  "single_word": false,
115
+ "special": false
116
  },
117
+ "14": {
118
+ "content": "<unused7>",
119
  "lstrip": false,
120
  "normalized": false,
121
  "rstrip": false,
122
  "single_word": false,
123
+ "special": false
124
  },
125
+ "15": {
126
+ "content": "<unused8>",
127
  "lstrip": false,
128
  "normalized": false,
129
  "rstrip": false,
130
  "single_word": false,
131
+ "special": false
132
  },
133
+ "16": {
134
+ "content": "<unused9>",
135
  "lstrip": false,
136
  "normalized": false,
137
  "rstrip": false,
138
  "single_word": false,
139
+ "special": false
140
  },
141
+ "17": {
142
+ "content": "<unused10>",
143
  "lstrip": false,
144
  "normalized": false,
145
  "rstrip": false,
146
  "single_word": false,
147
+ "special": false
148
  },
149
+ "18": {
150
+ "content": "<unused11>",
151
  "lstrip": false,
152
  "normalized": false,
153
  "rstrip": false,
154
  "single_word": false,
155
+ "special": false
156
  },
157
+ "19": {
158
+ "content": "<unused12>",
159
  "lstrip": false,
160
  "normalized": false,
161
  "rstrip": false,
162
  "single_word": false,
163
+ "special": false
164
  },
165
+ "20": {
166
+ "content": "<unused13>",
167
  "lstrip": false,
168
  "normalized": false,
169
  "rstrip": false,
170
  "single_word": false,
171
+ "special": false
172
  },
173
+ "21": {
174
+ "content": "<unused14>",
175
  "lstrip": false,
176
  "normalized": false,
177
  "rstrip": false,
178
  "single_word": false,
179
+ "special": false
180
  },
181
+ "22": {
182
+ "content": "<unused15>",
183
  "lstrip": false,
184
  "normalized": false,
185
  "rstrip": false,
186
  "single_word": false,
187
+ "special": false
188
  },
189
+ "23": {
190
+ "content": "<unused16>",
191
  "lstrip": false,
192
  "normalized": false,
193
  "rstrip": false,
194
  "single_word": false,
195
+ "special": false
196
  },
197
+ "24": {
198
+ "content": "<unused17>",
199
  "lstrip": false,
200
  "normalized": false,
201
  "rstrip": false,
202
  "single_word": false,
203
+ "special": false
204
  },
205
+ "25": {
206
+ "content": "<unused18>",
207
  "lstrip": false,
208
  "normalized": false,
209
  "rstrip": false,
210
  "single_word": false,
211
+ "special": false
212
  },
213
+ "26": {
214
+ "content": "<unused19>",
215
  "lstrip": false,
216
  "normalized": false,
217
  "rstrip": false,
218
  "single_word": false,
219
+ "special": false
220
  },
221
+ "27": {
222
+ "content": "<unused20>",
223
  "lstrip": false,
224
  "normalized": false,
225
  "rstrip": false,
226
  "single_word": false,
227
+ "special": false
228
  },
229
+ "28": {
230
+ "content": "<unused21>",
231
  "lstrip": false,
232
  "normalized": false,
233
  "rstrip": false,
234
  "single_word": false,
235
+ "special": false
236
  },
237
+ "29": {
238
+ "content": "<unused22>",
239
  "lstrip": false,
240
  "normalized": false,
241
  "rstrip": false,
242
  "single_word": false,
243
+ "special": false
244
  },
245
+ "30": {
246
+ "content": "<unused23>",
247
  "lstrip": false,
248
  "normalized": false,
249
  "rstrip": false,
250
  "single_word": false,
251
+ "special": false
252
  },
253
+ "31": {
254
+ "content": "<unused24>",
255
  "lstrip": false,
256
  "normalized": false,
257
  "rstrip": false,
258
  "single_word": false,
259
+ "special": false
260
  },
261
+ "32": {
262
+ "content": "<unused25>",
263
  "lstrip": false,
264
  "normalized": false,
265
  "rstrip": false,
266
  "single_word": false,
267
+ "special": false
268
  },
269
+ "33": {
270
+ "content": "<unused26>",
271
  "lstrip": false,
272
  "normalized": false,
273
  "rstrip": false,
274
  "single_word": false,
275
+ "special": false
276
  },
277
+ "34": {
278
+ "content": "<unused27>",
279
  "lstrip": false,
280
  "normalized": false,
281
  "rstrip": false,
282
  "single_word": false,
283
+ "special": false
284
  },
285
+ "35": {
286
+ "content": "<unused28>",
287
  "lstrip": false,
288
  "normalized": false,
289
  "rstrip": false,
290
  "single_word": false,
291
+ "special": false
292
  },
293
+ "36": {
294
+ "content": "<unused29>",
295
  "lstrip": false,
296
  "normalized": false,
297
  "rstrip": false,
298
  "single_word": false,
299
+ "special": false
300
  },
301
+ "37": {
302
+ "content": "<unused30>",
303
  "lstrip": false,
304
  "normalized": false,
305
  "rstrip": false,
306
  "single_word": false,
307
+ "special": false
308
  },
309
+ "38": {
310
+ "content": "<unused31>",
311
  "lstrip": false,
312
  "normalized": false,
313
  "rstrip": false,
314
  "single_word": false,
315
+ "special": false
316
  },
317
+ "39": {
318
+ "content": "<unused32>",
319
  "lstrip": false,
320
  "normalized": false,
321
  "rstrip": false,
322
  "single_word": false,
323
+ "special": false
324
  },
325
+ "40": {
326
+ "content": "<unused33>",
327
  "lstrip": false,
328
  "normalized": false,
329
  "rstrip": false,
330
  "single_word": false,
331
+ "special": false
332
  },
333
+ "41": {
334
+ "content": "<unused34>",
335
  "lstrip": false,
336
  "normalized": false,
337
  "rstrip": false,
338
  "single_word": false,
339
+ "special": false
340
  },
341
+ "42": {
342
+ "content": "<unused35>",
343
  "lstrip": false,
344
  "normalized": false,
345
  "rstrip": false,
346
  "single_word": false,
347
+ "special": false
348
  },
349
+ "43": {
350
+ "content": "<unused36>",
351
  "lstrip": false,
352
  "normalized": false,
353
  "rstrip": false,
354
  "single_word": false,
355
+ "special": false
356
  },
357
+ "44": {
358
+ "content": "<unused37>",
359
  "lstrip": false,
360
  "normalized": false,
361
  "rstrip": false,
362
  "single_word": false,
363
+ "special": false
364
  },
365
+ "45": {
366
+ "content": "<unused38>",
367
  "lstrip": false,
368
  "normalized": false,
369
  "rstrip": false,
370
  "single_word": false,
371
+ "special": false
372
  },
373
+ "46": {
374
+ "content": "<unused39>",
375
  "lstrip": false,
376
  "normalized": false,
377
  "rstrip": false,
378
  "single_word": false,
379
+ "special": false
380
  },
381
+ "47": {
382
+ "content": "<unused40>",
383
  "lstrip": false,
384
  "normalized": false,
385
  "rstrip": false,
386
  "single_word": false,
387
+ "special": false
388
  },
389
+ "48": {
390
+ "content": "<unused41>",
391
  "lstrip": false,
392
  "normalized": false,
393
  "rstrip": false,
394
  "single_word": false,
395
+ "special": false
396
  },
397
+ "49": {
398
+ "content": "<unused42>",
399
  "lstrip": false,
400
  "normalized": false,
401
  "rstrip": false,
402
  "single_word": false,
403
+ "special": false
404
  },
405
+ "50": {
406
+ "content": "<unused43>",
407
  "lstrip": false,
408
  "normalized": false,
409
  "rstrip": false,
410
  "single_word": false,
411
+ "special": false
412
  },
413
+ "51": {
414
+ "content": "<unused44>",
415
  "lstrip": false,
416
  "normalized": false,
417
  "rstrip": false,
418
  "single_word": false,
419
+ "special": false
420
  },
421
+ "52": {
422
+ "content": "<unused45>",
423
  "lstrip": false,
424
  "normalized": false,
425
  "rstrip": false,
426
  "single_word": false,
427
+ "special": false
428
  },
429
+ "53": {
430
+ "content": "<unused46>",
431
  "lstrip": false,
432
  "normalized": false,
433
  "rstrip": false,
434
  "single_word": false,
435
+ "special": false
436
  },
437
+ "54": {
438
+ "content": "<unused47>",
439
  "lstrip": false,
440
  "normalized": false,
441
  "rstrip": false,
442
  "single_word": false,
443
+ "special": false
444
  },
445
+ "55": {
446
+ "content": "<unused48>",
447
  "lstrip": false,
448
  "normalized": false,
449
  "rstrip": false,
450
  "single_word": false,
451
+ "special": false
452
  },
453
+ "56": {
454
+ "content": "<unused49>",
455
  "lstrip": false,
456
  "normalized": false,
457
  "rstrip": false,
458
  "single_word": false,
459
+ "special": false
460
  },
461
+ "57": {
462
+ "content": "<unused50>",
463
  "lstrip": false,
464
  "normalized": false,
465
  "rstrip": false,
466
  "single_word": false,
467
+ "special": false
468
  },
469
+ "58": {
470
+ "content": "<unused51>",
471
  "lstrip": false,
472
  "normalized": false,
473
  "rstrip": false,
474
  "single_word": false,
475
+ "special": false
476
  },
477
+ "59": {
478
+ "content": "<unused52>",
479
  "lstrip": false,
480
  "normalized": false,
481
  "rstrip": false,
482
  "single_word": false,
483
+ "special": false
484
  },
485
+ "60": {
486
+ "content": "<unused53>",
487
  "lstrip": false,
488
  "normalized": false,
489
  "rstrip": false,
490
  "single_word": false,
491
+ "special": false
492
  },
493
+ "61": {
494
+ "content": "<unused54>",
495
  "lstrip": false,
496
  "normalized": false,
497
  "rstrip": false,
498
  "single_word": false,
499
+ "special": false
500
  },
501
+ "62": {
502
+ "content": "<unused55>",
503
  "lstrip": false,
504
  "normalized": false,
505
  "rstrip": false,
506
  "single_word": false,
507
+ "special": false
508
  },
509
+ "63": {
510
+ "content": "<unused56>",
511
  "lstrip": false,
512
  "normalized": false,
513
  "rstrip": false,
514
  "single_word": false,
515
+ "special": false
516
  },
517
+ "64": {
518
+ "content": "<unused57>",
519
  "lstrip": false,
520
  "normalized": false,
521
  "rstrip": false,
522
  "single_word": false,
523
+ "special": false
524
  },
525
+ "65": {
526
+ "content": "<unused58>",
527
  "lstrip": false,
528
  "normalized": false,
529
  "rstrip": false,
530
  "single_word": false,
531
+ "special": false
532
  },
533
+ "66": {
534
+ "content": "<unused59>",
535
  "lstrip": false,
536
  "normalized": false,
537
  "rstrip": false,
538
  "single_word": false,
539
+ "special": false
540
  },
541
+ "67": {
542
+ "content": "<unused60>",
543
  "lstrip": false,
544
  "normalized": false,
545
  "rstrip": false,
546
  "single_word": false,
547
+ "special": false
548
  },
549
+ "68": {
550
+ "content": "<unused61>",
551
  "lstrip": false,
552
  "normalized": false,
553
  "rstrip": false,
554
  "single_word": false,
555
+ "special": false
556
  },
557
+ "69": {
558
+ "content": "<unused62>",
559
  "lstrip": false,
560
  "normalized": false,
561
  "rstrip": false,
562
  "single_word": false,
563
+ "special": false
564
  },
565
+ "70": {
566
+ "content": "<unused63>",
567
  "lstrip": false,
568
  "normalized": false,
569
  "rstrip": false,
570
  "single_word": false,
571
+ "special": false
572
  },
573
+ "71": {
574
+ "content": "<unused64>",
575
  "lstrip": false,
576
  "normalized": false,
577
  "rstrip": false,
578
  "single_word": false,
579
+ "special": false
580
  },
581
+ "72": {
582
+ "content": "<unused65>",
583
  "lstrip": false,
584
  "normalized": false,
585
  "rstrip": false,
586
  "single_word": false,
587
+ "special": false
588
  },
589
+ "73": {
590
+ "content": "<unused66>",
591
  "lstrip": false,
592
  "normalized": false,
593
  "rstrip": false,
594
  "single_word": false,
595
+ "special": false
596
  },
597
+ "74": {
598
+ "content": "<unused67>",
599
  "lstrip": false,
600
  "normalized": false,
601
  "rstrip": false,
602
  "single_word": false,
603
+ "special": false
604
  },
605
+ "75": {
606
+ "content": "<unused68>",
607
  "lstrip": false,
608
  "normalized": false,
609
  "rstrip": false,
610
  "single_word": false,
611
+ "special": false
612
  },
613
+ "76": {
614
+ "content": "<unused69>",
615
  "lstrip": false,
616
  "normalized": false,
617
  "rstrip": false,
618
  "single_word": false,
619
+ "special": false
620
  },
621
+ "77": {
622
+ "content": "<unused70>",
623
  "lstrip": false,
624
  "normalized": false,
625
  "rstrip": false,
626
  "single_word": false,
627
+ "special": false
628
  },
629
+ "78": {
630
+ "content": "<unused71>",
631
  "lstrip": false,
632
  "normalized": false,
633
  "rstrip": false,
634
  "single_word": false,
635
+ "special": false
636
  },
637
+ "79": {
638
+ "content": "<unused72>",
639
  "lstrip": false,
640
  "normalized": false,
641
  "rstrip": false,
642
  "single_word": false,
643
+ "special": false
644
  },
645
+ "80": {
646
+ "content": "<unused73>",
647
  "lstrip": false,
648
  "normalized": false,
649
  "rstrip": false,
650
  "single_word": false,
651
+ "special": false
652
  },
653
+ "81": {
654
+ "content": "<unused74>",
655
  "lstrip": false,
656
  "normalized": false,
657
  "rstrip": false,
658
  "single_word": false,
659
+ "special": false
660
  },
661
+ "82": {
662
+ "content": "<unused75>",
663
  "lstrip": false,
664
  "normalized": false,
665
  "rstrip": false,
666
  "single_word": false,
667
+ "special": false
668
  },
669
+ "83": {
670
+ "content": "<unused76>",
671
  "lstrip": false,
672
  "normalized": false,
673
  "rstrip": false,
674
  "single_word": false,
675
+ "special": false
676
  },
677
+ "84": {
678
+ "content": "<unused77>",
679
  "lstrip": false,
680
  "normalized": false,
681
  "rstrip": false,
682
  "single_word": false,
683
+ "special": false
684
  },
685
+ "85": {
686
+ "content": "<unused78>",
687
  "lstrip": false,
688
  "normalized": false,
689
  "rstrip": false,
690
  "single_word": false,
691
+ "special": false
692
  },
693
+ "86": {
694
+ "content": "<unused79>",
695
  "lstrip": false,
696
  "normalized": false,
697
  "rstrip": false,
698
  "single_word": false,
699
+ "special": false
700
  },
701
+ "87": {
702
+ "content": "<unused80>",
703
  "lstrip": false,
704
  "normalized": false,
705
  "rstrip": false,
706
  "single_word": false,
707
+ "special": false
708
  },
709
+ "88": {
710
+ "content": "<unused81>",
711
  "lstrip": false,
712
  "normalized": false,
713
  "rstrip": false,
714
  "single_word": false,
715
+ "special": false
716
  },
717
+ "89": {
718
+ "content": "<unused82>",
719
  "lstrip": false,
720
  "normalized": false,
721
  "rstrip": false,
722
  "single_word": false,
723
+ "special": false
724
  },
725
+ "90": {
726
+ "content": "<unused83>",
727
  "lstrip": false,
728
  "normalized": false,
729
  "rstrip": false,
730
  "single_word": false,
731
+ "special": false
732
  },
733
+ "91": {
734
+ "content": "<unused84>",
735
  "lstrip": false,
736
  "normalized": false,
737
  "rstrip": false,
738
  "single_word": false,
739
+ "special": false
740
  },
741
+ "92": {
742
+ "content": "<unused85>",
743
  "lstrip": false,
744
  "normalized": false,
745
  "rstrip": false,
746
  "single_word": false,
747
+ "special": false
748
  },
749
+ "93": {
750
+ "content": "<unused86>",
751
  "lstrip": false,
752
  "normalized": false,
753
  "rstrip": false,
754
  "single_word": false,
755
+ "special": false
756
  },
757
+ "94": {
758
+ "content": "<unused87>",
759
  "lstrip": false,
760
  "normalized": false,
761
  "rstrip": false,
762
  "single_word": false,
763
+ "special": false
764
  },
765
+ "95": {
766
+ "content": "<unused88>",
767
  "lstrip": false,
768
  "normalized": false,
769
  "rstrip": false,
770
  "single_word": false,
771
+ "special": false
772
  },
773
+ "96": {
774
+ "content": "<unused89>",
775
  "lstrip": false,
776
  "normalized": false,
777
  "rstrip": false,
778
  "single_word": false,
779
+ "special": false
780
  },
781
+ "97": {
782
+ "content": "<unused90>",
783
  "lstrip": false,
784
  "normalized": false,
785
  "rstrip": false,
786
  "single_word": false,
787
+ "special": false
788
  },
789
+ "98": {
790
+ "content": "<unused91>",
791
  "lstrip": false,
792
  "normalized": false,
793
  "rstrip": false,
794
  "single_word": false,
795
+ "special": false
796
  },
797
+ "99": {
798
+ "content": "<unused92>",
799
  "lstrip": false,
800
  "normalized": false,
801
  "rstrip": false,
802
  "single_word": false,
803
+ "special": false
804
  },
805
+ "100": {
806
+ "content": "<unused93>",
807
  "lstrip": false,
808
  "normalized": false,
809
  "rstrip": false,
810
  "single_word": false,
811
+ "special": false
812
  },
813
+ "101": {
814
+ "content": "<unused94>",
815
  "lstrip": false,
816
  "normalized": false,
817
  "rstrip": false,
818
  "single_word": false,
819
+ "special": false
820
  },
821
+ "102": {
822
+ "content": "<unused95>",
823
  "lstrip": false,
824
  "normalized": false,
825
  "rstrip": false,
826
  "single_word": false,
827
+ "special": false
828
  },
829
+ "103": {
830
+ "content": "<unused96>",
831
  "lstrip": false,
832
  "normalized": false,
833
  "rstrip": false,
834
  "single_word": false,
835
+ "special": false
836
  },
837
+ "104": {
838
+ "content": "<unused97>",
839
  "lstrip": false,
840
  "normalized": false,
841
  "rstrip": false,
842
  "single_word": false,
843
+ "special": false
844
  },
845
+ "105": {
846
+ "content": "<unused98>",
847
  "lstrip": false,
848
  "normalized": false,
849
  "rstrip": false,
850
  "single_word": false,
851
+ "special": false
852
  },
853
+ "106": {
854
+ "content": "<start_of_turn>",
855
  "lstrip": false,
856
  "normalized": false,
857
  "rstrip": false,
858
  "single_word": false,
859
  "special": true
860
  },
861
+ "107": {
862
+ "content": "<end_of_turn>",
863
  "lstrip": false,
864
  "normalized": false,
865
  "rstrip": false,
866
  "single_word": false,
867
  "special": true
868
  },
869
+ "108": {
870
+ "content": "\n",
871
  "lstrip": false,
872
  "normalized": false,
873
  "rstrip": false,
874
  "single_word": false,
875
+ "special": false
876
  },
877
+ "109": {
878
+ "content": "\n\n",
879
  "lstrip": false,
880
  "normalized": false,
881
  "rstrip": false,
882
  "single_word": false,
883
+ "special": false
884
  },
885
+ "110": {
886
+ "content": "\n\n\n",
887
  "lstrip": false,
888
  "normalized": false,
889
  "rstrip": false,
890
  "single_word": false,
891
+ "special": false
892
  },
893
+ "111": {
894
+ "content": "\n\n\n\n",
895
  "lstrip": false,
896
  "normalized": false,
897
  "rstrip": false,
898
  "single_word": false,
899
+ "special": false
900
  },
901
+ "112": {
902
+ "content": "\n\n\n\n\n",
903
  "lstrip": false,
904
  "normalized": false,
905
  "rstrip": false,
906
  "single_word": false,
907
+ "special": false
908
  },
909
+ "113": {
910
+ "content": "\n\n\n\n\n\n",
911
  "lstrip": false,
912
  "normalized": false,
913
  "rstrip": false,
914
  "single_word": false,
915
+ "special": false
916
  },
917
+ "114": {
918
+ "content": "\n\n\n\n\n\n\n",
919
  "lstrip": false,
920
  "normalized": false,
921
  "rstrip": false,
922
  "single_word": false,
923
+ "special": false
924
  },
925
+ "115": {
926
+ "content": "\n\n\n\n\n\n\n\n",
927
  "lstrip": false,
928
  "normalized": false,
929
  "rstrip": false,
930
  "single_word": false,
931
+ "special": false
932
  },
933
+ "116": {
934
+ "content": "\n\n\n\n\n\n\n\n\n",
935
  "lstrip": false,
936
  "normalized": false,
937
  "rstrip": false,
938
  "single_word": false,
939
+ "special": false
940
  },
941
+ "117": {
942
+ "content": "\n\n\n\n\n\n\n\n\n\n",
943
  "lstrip": false,
944
  "normalized": false,
945
  "rstrip": false,
946
  "single_word": false,
947
+ "special": false
948
  },
949
+ "118": {
950
+ "content": "\n\n\n\n\n\n\n\n\n\n\n",
951
  "lstrip": false,
952
  "normalized": false,
953
  "rstrip": false,
954
  "single_word": false,
955
+ "special": false
956
  },
957
+ "119": {
958
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
959
  "lstrip": false,
960
  "normalized": false,
961
  "rstrip": false,
962
  "single_word": false,
963
+ "special": false
964
  },
965
+ "120": {
966
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
967
  "lstrip": false,
968
  "normalized": false,
969
  "rstrip": false,
970
  "single_word": false,
971
+ "special": false
972
  },
973
+ "121": {
974
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
975
  "lstrip": false,
976
  "normalized": false,
977
  "rstrip": false,
978
  "single_word": false,
979
+ "special": false
980
  },
981
+ "122": {
982
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
983
  "lstrip": false,
984
  "normalized": false,
985
  "rstrip": false,
986
  "single_word": false,
987
+ "special": false
988
  },
989
+ "123": {
990
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
991
  "lstrip": false,
992
  "normalized": false,
993
  "rstrip": false,
994
  "single_word": false,
995
+ "special": false
996
  },
997
+ "124": {
998
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
999
  "lstrip": false,
1000
  "normalized": false,
1001
  "rstrip": false,
1002
  "single_word": false,
1003
+ "special": false
1004
  },
1005
+ "125": {
1006
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1007
  "lstrip": false,
1008
  "normalized": false,
1009
  "rstrip": false,
1010
  "single_word": false,
1011
+ "special": false
1012
  },
1013
+ "126": {
1014
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1015
  "lstrip": false,
1016
  "normalized": false,
1017
  "rstrip": false,
1018
  "single_word": false,
1019
+ "special": false
1020
  },
1021
+ "127": {
1022
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1023
  "lstrip": false,
1024
  "normalized": false,
1025
  "rstrip": false,
1026
  "single_word": false,
1027
+ "special": false
1028
  },
1029
+ "128": {
1030
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1031
  "lstrip": false,
1032
  "normalized": false,
1033
  "rstrip": false,
1034
  "single_word": false,
1035
+ "special": false
1036
  },
1037
+ "129": {
1038
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1039
  "lstrip": false,
1040
  "normalized": false,
1041
  "rstrip": false,
1042
  "single_word": false,
1043
+ "special": false
1044
  },
1045
+ "130": {
1046
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1047
  "lstrip": false,
1048
  "normalized": false,
1049
  "rstrip": false,
1050
  "single_word": false,
1051
+ "special": false
1052
  },
1053
+ "131": {
1054
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1055
  "lstrip": false,
1056
  "normalized": false,
1057
  "rstrip": false,
1058
  "single_word": false,
1059
+ "special": false
1060
  },
1061
+ "132": {
1062
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1063
  "lstrip": false,
1064
  "normalized": false,
1065
  "rstrip": false,
1066
  "single_word": false,
1067
+ "special": false
1068
  },
1069
+ "133": {
1070
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1071
  "lstrip": false,
1072
  "normalized": false,
1073
  "rstrip": false,
1074
  "single_word": false,
1075
+ "special": false
1076
  },
1077
+ "134": {
1078
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1079
  "lstrip": false,
1080
  "normalized": false,
1081
  "rstrip": false,
1082
  "single_word": false,
1083
+ "special": false
1084
  },
1085
+ "135": {
1086
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1087
  "lstrip": false,
1088
  "normalized": false,
1089
  "rstrip": false,
1090
  "single_word": false,
1091
+ "special": false
1092
  },
1093
+ "136": {
1094
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1095
  "lstrip": false,
1096
  "normalized": false,
1097
  "rstrip": false,
1098
  "single_word": false,
1099
+ "special": false
1100
  },
1101
+ "137": {
1102
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1103
  "lstrip": false,
1104
  "normalized": false,
1105
  "rstrip": false,
1106
  "single_word": false,
1107
+ "special": false
1108
  },
1109
+ "138": {
1110
+ "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
1111
  "lstrip": false,
1112
  "normalized": false,
1113
  "rstrip": false,
1114
  "single_word": false,
1115
+ "special": false
1116
  },
1117
+ "139": {
1118
+ "content": "▁▁",
1119
  "lstrip": false,
1120
  "normalized": false,
1121
  "rstrip": false,
1122
  "single_word": false,
1123
+ "special": false
1124
  },
1125
+ "140": {
1126
+ "content": "▁▁▁",
1127
  "lstrip": false,
1128
  "normalized": false,
1129
  "rstrip": false,
1130
  "single_word": false,
1131
+ "special": false
1132
  },
1133
+ "141": {
1134
+ "content": "▁▁▁▁",
1135
  "lstrip": false,
1136
  "normalized": false,
1137
  "rstrip": false,
1138
  "single_word": false,
1139
+ "special": false
1140
  },
1141
+ "142": {
1142
+ "content": "▁▁▁▁▁",
1143
  "lstrip": false,
1144
  "normalized": false,
1145
  "rstrip": false,
1146
  "single_word": false,
1147
+ "special": false
1148
  },
1149
+ "143": {
1150
+ "content": "▁▁▁▁▁▁",
1151
  "lstrip": false,
1152
  "normalized": false,
1153
  "rstrip": false,
1154
  "single_word": false,
1155
+ "special": false
1156
  },
1157
+ "144": {
1158
+ "content": "▁▁▁▁▁▁▁",
1159
  "lstrip": false,
1160
  "normalized": false,
1161
  "rstrip": false,
1162
  "single_word": false,
1163
+ "special": false
1164
  },
1165
+ "145": {
1166
+ "content": "▁▁▁▁▁▁▁▁",
1167
  "lstrip": false,
1168
  "normalized": false,
1169
  "rstrip": false,
1170
  "single_word": false,
1171
+ "special": false
1172
  },
1173
+ "146": {
1174
+ "content": "▁▁▁▁▁▁▁▁▁",
1175
  "lstrip": false,
1176
  "normalized": false,
1177
  "rstrip": false,
1178
  "single_word": false,
1179
+ "special": false
1180
  },
1181
+ "147": {
1182
+ "content": "▁▁▁▁▁▁▁▁▁▁",
1183
  "lstrip": false,
1184
  "normalized": false,
1185
  "rstrip": false,
1186
  "single_word": false,
1187
+ "special": false
1188
  },
1189
+ "148": {
1190
+ "content": "▁▁▁▁▁▁▁▁▁▁▁",
1191
  "lstrip": false,
1192
  "normalized": false,
1193
  "rstrip": false,
1194
  "single_word": false,
1195
+ "special": false
1196
  },
1197
+ "149": {
1198
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
1199
  "lstrip": false,
1200
  "normalized": false,
1201
  "rstrip": false,
1202
  "single_word": false,
1203
+ "special": false
1204
  },
1205
+ "150": {
1206
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
1207
  "lstrip": false,
1208
  "normalized": false,
1209
  "rstrip": false,
1210
  "single_word": false,
1211
+ "special": false
1212
  },
1213
+ "151": {
1214
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1215
  "lstrip": false,
1216
  "normalized": false,
1217
  "rstrip": false,
1218
  "single_word": false,
1219
+ "special": false
1220
  },
1221
+ "152": {
1222
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1223
  "lstrip": false,
1224
  "normalized": false,
1225
  "rstrip": false,
1226
  "single_word": false,
1227
+ "special": false
1228
  },
1229
+ "153": {
1230
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1231
  "lstrip": false,
1232
  "normalized": false,
1233
  "rstrip": false,
1234
  "single_word": false,
1235
+ "special": false
1236
  },
1237
+ "154": {
1238
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1239
  "lstrip": false,
1240
  "normalized": false,
1241
  "rstrip": false,
1242
  "single_word": false,
1243
+ "special": false
1244
  },
1245
+ "155": {
1246
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1247
  "lstrip": false,
1248
  "normalized": false,
1249
  "rstrip": false,
1250
  "single_word": false,
1251
+ "special": false
1252
  },
1253
+ "156": {
1254
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1255
  "lstrip": false,
1256
  "normalized": false,
1257
  "rstrip": false,
1258
  "single_word": false,
1259
+ "special": false
1260
  },
1261
+ "157": {
1262
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1263
  "lstrip": false,
1264
  "normalized": false,
1265
  "rstrip": false,
1266
  "single_word": false,
1267
+ "special": false
1268
  },
1269
+ "158": {
1270
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1271
  "lstrip": false,
1272
  "normalized": false,
1273
  "rstrip": false,
1274
  "single_word": false,
1275
+ "special": false
1276
  },
1277
+ "159": {
1278
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1279
  "lstrip": false,
1280
  "normalized": false,
1281
  "rstrip": false,
1282
  "single_word": false,
1283
+ "special": false
1284
  },
1285
+ "160": {
1286
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1287
  "lstrip": false,
1288
  "normalized": false,
1289
  "rstrip": false,
1290
  "single_word": false,
1291
+ "special": false
1292
  },
1293
+ "161": {
1294
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1295
  "lstrip": false,
1296
  "normalized": false,
1297
  "rstrip": false,
1298
  "single_word": false,
1299
+ "special": false
1300
  },
1301
+ "162": {
1302
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1303
  "lstrip": false,
1304
  "normalized": false,
1305
  "rstrip": false,
1306
  "single_word": false,
1307
+ "special": false
1308
  },
1309
+ "163": {
1310
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1311
  "lstrip": false,
1312
  "normalized": false,
1313
  "rstrip": false,
1314
  "single_word": false,
1315
+ "special": false
1316
  },
1317
+ "164": {
1318
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1319
  "lstrip": false,
1320
  "normalized": false,
1321
  "rstrip": false,
1322
  "single_word": false,
1323
+ "special": false
1324
  },
1325
+ "165": {
1326
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1327
  "lstrip": false,
1328
  "normalized": false,
1329
  "rstrip": false,
1330
  "single_word": false,
1331
+ "special": false
1332
  },
1333
+ "166": {
1334
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1335
  "lstrip": false,
1336
  "normalized": false,
1337
  "rstrip": false,
1338
  "single_word": false,
1339
+ "special": false
1340
  },
1341
+ "167": {
1342
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1343
  "lstrip": false,
1344
  "normalized": false,
1345
  "rstrip": false,
1346
  "single_word": false,
1347
+ "special": false
1348
  },
1349
+ "168": {
1350
+ "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
1351
  "lstrip": false,
1352
  "normalized": false,
1353
  "rstrip": false,
1354
  "single_word": false,
1355
+ "special": false
1356
  },
1357
+ "169": {
1358
+ "content": "<table>",
1359
  "lstrip": false,
1360
  "normalized": false,
1361
  "rstrip": false,
1362
  "single_word": false,
1363
+ "special": false
1364
  },
1365
+ "170": {
1366
+ "content": "<caption>",
1367
  "lstrip": false,
1368
  "normalized": false,
1369
  "rstrip": false,
1370
  "single_word": false,
1371
+ "special": false
1372
  },
1373
+ "171": {
1374
+ "content": "<thead>",
1375
  "lstrip": false,
1376
  "normalized": false,
1377
  "rstrip": false,
1378
  "single_word": false,
1379
+ "special": false
1380
  },
1381
+ "172": {
1382
+ "content": "<tbody>",
1383
  "lstrip": false,
1384
  "normalized": false,
1385
  "rstrip": false,
1386
  "single_word": false,
1387
+ "special": false
1388
  },
1389
+ "173": {
1390
+ "content": "<tfoot>",
1391
  "lstrip": false,
1392
  "normalized": false,
1393
  "rstrip": false,
1394
  "single_word": false,
1395
+ "special": false
1396
  },
1397
+ "174": {
1398
+ "content": "<tr>",
1399
  "lstrip": false,
1400
  "normalized": false,
1401
  "rstrip": false,
1402
  "single_word": false,
1403
+ "special": false
1404
  },
1405
+ "175": {
1406
+ "content": "<th>",
1407
  "lstrip": false,
1408
  "normalized": false,
1409
  "rstrip": false,
1410
  "single_word": false,
1411
+ "special": false
1412
  },
1413
+ "176": {
1414
+ "content": "<td>",
1415
  "lstrip": false,
1416
  "normalized": false,
1417
  "rstrip": false,
1418
  "single_word": false,
1419
+ "special": false
1420
  },
1421
+ "177": {
1422
+ "content": "</table>",
1423
  "lstrip": false,
1424
  "normalized": false,
1425
  "rstrip": false,
1426
  "single_word": false,
1427
+ "special": false
1428
  },
1429
+ "178": {
1430
+ "content": "</caption>",
1431
  "lstrip": false,
1432
  "normalized": false,
1433
  "rstrip": false,
1434
  "single_word": false,
1435
+ "special": false
1436
  },
1437
+ "179": {
1438
+ "content": "</thead>",
1439
  "lstrip": false,
1440
  "normalized": false,
1441
  "rstrip": false,
1442
  "single_word": false,
1443
+ "special": false
1444
  },
1445
+ "180": {
1446
+ "content": "</tbody>",
1447
  "lstrip": false,
1448
  "normalized": false,
1449
  "rstrip": false,
1450
  "single_word": false,
1451
+ "special": false
1452
  },
1453
+ "181": {
1454
+ "content": "</tfoot>",
1455
  "lstrip": false,
1456
  "normalized": false,
1457
  "rstrip": false,
1458
  "single_word": false,
1459
+ "special": false
1460
  },
1461
+ "182": {
1462
+ "content": "</tr>",
1463
  "lstrip": false,
1464
  "normalized": false,
1465
  "rstrip": false,
1466
  "single_word": false,
1467
+ "special": false
1468
  },
1469
+ "183": {
1470
+ "content": "</th>",
1471
  "lstrip": false,
1472
  "normalized": false,
1473
  "rstrip": false,
1474
  "single_word": false,
1475
+ "special": false
1476
  },
1477
+ "184": {
1478
+ "content": "</td>",
1479
  "lstrip": false,
1480
  "normalized": false,
1481
  "rstrip": false,
1482
  "single_word": false,
1483
+ "special": false
1484
  },
1485
+ "185": {
1486
+ "content": "<h1>",
1487
  "lstrip": false,
1488
  "normalized": false,
1489
  "rstrip": false,
1490
  "single_word": false,
1491
+ "special": false
1492
  },
1493
+ "186": {
1494
+ "content": "<h2>",
1495
  "lstrip": false,
1496
  "normalized": false,
1497
  "rstrip": false,
1498
  "single_word": false,
1499
+ "special": false
1500
  },
1501
+ "187": {
1502
+ "content": "<h3>",
1503
  "lstrip": false,
1504
  "normalized": false,
1505
  "rstrip": false,
1506
  "single_word": false,
1507
+ "special": false
1508
  },
1509
+ "188": {
1510
+ "content": "<h4>",
1511
  "lstrip": false,
1512
  "normalized": false,
1513
  "rstrip": false,
1514
  "single_word": false,
1515
+ "special": false
1516
  },
1517
+ "189": {
1518
+ "content": "<h5>",
1519
  "lstrip": false,
1520
  "normalized": false,
1521
  "rstrip": false,
1522
  "single_word": false,
1523
+ "special": false
1524
  },
1525
+ "190": {
1526
+ "content": "<h6>",
1527
  "lstrip": false,
1528
  "normalized": false,
1529
  "rstrip": false,
1530
  "single_word": false,
1531
+ "special": false
1532
  },
1533
+ "191": {
1534
+ "content": "<blockquote>",
1535
  "lstrip": false,
1536
  "normalized": false,
1537
  "rstrip": false,
1538
  "single_word": false,
1539
+ "special": false
1540
  },
1541
+ "192": {
1542
+ "content": "</h1>",
1543
  "lstrip": false,
1544
  "normalized": false,
1545
  "rstrip": false,
1546
  "single_word": false,
1547
+ "special": false
1548
  },
1549
+ "193": {
1550
+ "content": "</h2>",
1551
  "lstrip": false,
1552
  "normalized": false,
1553
  "rstrip": false,
1554
  "single_word": false,
1555
+ "special": false
1556
  },
1557
+ "194": {
1558
+ "content": "</h3>",
1559
  "lstrip": false,
1560
  "normalized": false,
1561
  "rstrip": false,
1562
  "single_word": false,
1563
+ "special": false
1564
  },
1565
+ "195": {
1566
+ "content": "</h4>",
1567
  "lstrip": false,
1568
  "normalized": false,
1569
  "rstrip": false,
1570
  "single_word": false,
1571
+ "special": false
1572
  },
1573
+ "196": {
1574
+ "content": "</h5>",
1575
  "lstrip": false,
1576
  "normalized": false,
1577
  "rstrip": false,
1578
  "single_word": false,
1579
+ "special": false
1580
  },
1581
+ "197": {
1582
+ "content": "</h6>",
1583
  "lstrip": false,
1584
  "normalized": false,
1585
  "rstrip": false,
1586
  "single_word": false,
1587
+ "special": false
1588
  },
1589
+ "198": {
1590
+ "content": "</blockquote>",
1591
  "lstrip": false,
1592
  "normalized": false,
1593
  "rstrip": false,
1594
  "single_word": false,
1595
+ "special": false
1596
  },
1597
+ "199": {
1598
+ "content": "<strong>",
1599
  "lstrip": false,
1600
  "normalized": false,
1601
  "rstrip": false,
1602
  "single_word": false,
1603
+ "special": false
1604
  },
1605
+ "200": {
1606
+ "content": "<em>",
1607
  "lstrip": false,
1608
  "normalized": false,
1609
  "rstrip": false,
1610
  "single_word": false,
1611
+ "special": false
1612
  },
1613
+ "201": {
1614
+ "content": "<b>",
1615
  "lstrip": false,
1616
  "normalized": false,
1617
  "rstrip": false,
1618
  "single_word": false,
1619
+ "special": false
1620
  },
1621
+ "202": {
1622
+ "content": "<i>",
1623
  "lstrip": false,
1624
  "normalized": false,
1625
  "rstrip": false,
1626
  "single_word": false,
1627
+ "special": false
1628
  },
1629
+ "203": {
1630
+ "content": "<u>",
1631
  "lstrip": false,
1632
  "normalized": false,
1633
  "rstrip": false,
1634
  "single_word": false,
1635
+ "special": false
1636
  },
1637
+ "204": {
1638
+ "content": "<s>",
1639
  "lstrip": false,
1640
  "normalized": false,
1641
  "rstrip": false,
1642
  "single_word": false,
1643
+ "special": false
1644
  },
1645
+ "205": {
1646
+ "content": "<sub>",
1647
  "lstrip": false,
1648
  "normalized": false,
1649
  "rstrip": false,
1650
  "single_word": false,
1651
+ "special": false
1652
  },
1653
+ "206": {
1654
+ "content": "<sup>",
1655
  "lstrip": false,
1656
  "normalized": false,
1657
  "rstrip": false,
1658
  "single_word": false,
1659
+ "special": false
1660
  },
1661
+ "207": {
1662
+ "content": "<code>",
1663
  "lstrip": false,
1664
  "normalized": false,
1665
  "rstrip": false,
1666
  "single_word": false,
1667
+ "special": false
1668
  },
1669
+ "208": {
1670
+ "content": "</strong>",
1671
  "lstrip": false,
1672
  "normalized": false,
1673
  "rstrip": false,
1674
  "single_word": false,
1675
+ "special": false
1676
  },
1677
+ "209": {
1678
+ "content": "</em>",
1679
  "lstrip": false,
1680
  "normalized": false,
1681
  "rstrip": false,
1682
  "single_word": false,
1683
+ "special": false
1684
  },
1685
+ "210": {
1686
+ "content": "</b>",
1687
  "lstrip": false,
1688
  "normalized": false,
1689
  "rstrip": false,
1690
  "single_word": false,
1691
+ "special": false
1692
  },
1693
+ "211": {
1694
+ "content": "</i>",
1695
  "lstrip": false,
1696
  "normalized": false,
1697
  "rstrip": false,
1698
  "single_word": false,
1699
+ "special": false
1700
  },
1701
+ "212": {
1702
+ "content": "</u>",
1703
  "lstrip": false,
1704
  "normalized": false,
1705
  "rstrip": false,
1706
  "single_word": false,
1707
+ "special": false
1708
  },
1709
+ "213": {
1710
+ "content": "</s>",
1711
  "lstrip": false,
1712
  "normalized": false,
1713
  "rstrip": false,
1714
  "single_word": false,
1715
+ "special": false
1716
  },
1717
+ "214": {
1718
+ "content": "</sub>",
1719
  "lstrip": false,
1720
  "normalized": false,
1721
  "rstrip": false,
1722
  "single_word": false,
1723
+ "special": false
1724
  },
1725
+ "215": {
1726
+ "content": "</sup>",
1727
  "lstrip": false,
1728
  "normalized": false,
1729
  "rstrip": false,
1730
  "single_word": false,
1731
+ "special": false
1732
  },
1733
+ "216": {
1734
+ "content": "</code>",
1735
  "lstrip": false,
1736
  "normalized": false,
1737
  "rstrip": false,
1738
  "single_word": false,
1739
+ "special": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1740
  }
1741
  },
1742
+ "additional_special_tokens": [
1743
+ "<start_of_turn>",
1744
+ "<end_of_turn>"
 
 
 
1745
  ],
1746
+ "bos_token": "<bos>",
1747
+ "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
1748
+ "clean_up_tokenization_spaces": false,
1749
+ "eos_token": "<eos>",
1750
  "model_max_length": 8192,
1751
+ "pad_token": "<pad>",
1752
  "padding_side": "left",
1753
+ "sp_model_kwargs": {},
1754
+ "spaces_between_special_tokens": false,
1755
+ "tokenizer_class": "GemmaTokenizer",
1756
+ "unk_token": "<unk>",
1757
+ "use_default_system_prompt": false
1758
  }