gsaltintas commited on
Commit
7d273d1
·
verified ·
1 Parent(s): 78b1942

Upload folder using huggingface_hub

Browse files
Files changed (4) hide show
  1. README.md +1 -1
  2. tokenizer.json +92 -92
  3. tokenizer_config.json +92 -92
  4. vocab.json +103 -103
README.md CHANGED
@@ -46,4 +46,4 @@ tokens = tokenizer.encode("Hello, world!")
46
  ## Sample Encoding
47
  | Text | Tokens | Token IDs |
48
  |------|--------|-----------|
49
- | `1234500119 mod 67` | `12, 34, 50, 0, 11, 9, , mod, , 67` | `65, 74, 35, 8, 7, 21, 6, 4, 6, 62` |
 
46
  ## Sample Encoding
47
  | Text | Tokens | Token IDs |
48
  |------|--------|-----------|
49
+ | `1234500119 mod 67` | `12, 34, 50, 0, 11, 9, , mod, , 67` | `60, 37, 92, 8, 12, 62, 6, 4, 6, 68` |
tokenizer.json CHANGED
@@ -68,7 +68,7 @@
68
  },
69
  {
70
  "id": 7,
71
- "content": "11",
72
  "single_word": false,
73
  "lstrip": false,
74
  "rstrip": false,
@@ -86,7 +86,7 @@
86
  },
87
  {
88
  "id": 9,
89
- "content": "61",
90
  "single_word": false,
91
  "lstrip": false,
92
  "rstrip": false,
@@ -95,7 +95,7 @@
95
  },
96
  {
97
  "id": 10,
98
- "content": "72",
99
  "single_word": false,
100
  "lstrip": false,
101
  "rstrip": false,
@@ -104,7 +104,7 @@
104
  },
105
  {
106
  "id": 11,
107
- "content": "3",
108
  "single_word": false,
109
  "lstrip": false,
110
  "rstrip": false,
@@ -113,7 +113,7 @@
113
  },
114
  {
115
  "id": 12,
116
- "content": "27",
117
  "single_word": false,
118
  "lstrip": false,
119
  "rstrip": false,
@@ -122,7 +122,7 @@
122
  },
123
  {
124
  "id": 13,
125
- "content": "5",
126
  "single_word": false,
127
  "lstrip": false,
128
  "rstrip": false,
@@ -131,7 +131,7 @@
131
  },
132
  {
133
  "id": 14,
134
- "content": "18",
135
  "single_word": false,
136
  "lstrip": false,
137
  "rstrip": false,
@@ -140,7 +140,7 @@
140
  },
141
  {
142
  "id": 15,
143
- "content": "90",
144
  "single_word": false,
145
  "lstrip": false,
146
  "rstrip": false,
@@ -149,7 +149,7 @@
149
  },
150
  {
151
  "id": 16,
152
- "content": "21",
153
  "single_word": false,
154
  "lstrip": false,
155
  "rstrip": false,
@@ -158,7 +158,7 @@
158
  },
159
  {
160
  "id": 17,
161
- "content": "17",
162
  "single_word": false,
163
  "lstrip": false,
164
  "rstrip": false,
@@ -167,7 +167,7 @@
167
  },
168
  {
169
  "id": 18,
170
- "content": "28",
171
  "single_word": false,
172
  "lstrip": false,
173
  "rstrip": false,
@@ -176,7 +176,7 @@
176
  },
177
  {
178
  "id": 19,
179
- "content": "42",
180
  "single_word": false,
181
  "lstrip": false,
182
  "rstrip": false,
@@ -185,7 +185,7 @@
185
  },
186
  {
187
  "id": 20,
188
- "content": "58",
189
  "single_word": false,
190
  "lstrip": false,
191
  "rstrip": false,
@@ -194,7 +194,7 @@
194
  },
195
  {
196
  "id": 21,
197
- "content": "9",
198
  "single_word": false,
199
  "lstrip": false,
200
  "rstrip": false,
@@ -203,7 +203,7 @@
203
  },
204
  {
205
  "id": 22,
206
- "content": "36",
207
  "single_word": false,
208
  "lstrip": false,
209
  "rstrip": false,
@@ -212,7 +212,7 @@
212
  },
213
  {
214
  "id": 23,
215
- "content": "76",
216
  "single_word": false,
217
  "lstrip": false,
218
  "rstrip": false,
@@ -221,7 +221,7 @@
221
  },
222
  {
223
  "id": 24,
224
- "content": "38",
225
  "single_word": false,
226
  "lstrip": false,
227
  "rstrip": false,
@@ -230,7 +230,7 @@
230
  },
231
  {
232
  "id": 25,
233
- "content": "83",
234
  "single_word": false,
235
  "lstrip": false,
236
  "rstrip": false,
@@ -239,7 +239,7 @@
239
  },
240
  {
241
  "id": 26,
242
- "content": "89",
243
  "single_word": false,
244
  "lstrip": false,
245
  "rstrip": false,
@@ -248,7 +248,7 @@
248
  },
249
  {
250
  "id": 27,
251
- "content": "2",
252
  "single_word": false,
253
  "lstrip": false,
254
  "rstrip": false,
@@ -257,7 +257,7 @@
257
  },
258
  {
259
  "id": 28,
260
- "content": "10",
261
  "single_word": false,
262
  "lstrip": false,
263
  "rstrip": false,
@@ -266,7 +266,7 @@
266
  },
267
  {
268
  "id": 29,
269
- "content": "81",
270
  "single_word": false,
271
  "lstrip": false,
272
  "rstrip": false,
@@ -275,7 +275,7 @@
275
  },
276
  {
277
  "id": 30,
278
- "content": "35",
279
  "single_word": false,
280
  "lstrip": false,
281
  "rstrip": false,
@@ -284,7 +284,7 @@
284
  },
285
  {
286
  "id": 31,
287
- "content": "63",
288
  "single_word": false,
289
  "lstrip": false,
290
  "rstrip": false,
@@ -293,7 +293,7 @@
293
  },
294
  {
295
  "id": 32,
296
- "content": "94",
297
  "single_word": false,
298
  "lstrip": false,
299
  "rstrip": false,
@@ -302,7 +302,7 @@
302
  },
303
  {
304
  "id": 33,
305
- "content": "54",
306
  "single_word": false,
307
  "lstrip": false,
308
  "rstrip": false,
@@ -311,7 +311,7 @@
311
  },
312
  {
313
  "id": 34,
314
- "content": "87",
315
  "single_word": false,
316
  "lstrip": false,
317
  "rstrip": false,
@@ -320,7 +320,7 @@
320
  },
321
  {
322
  "id": 35,
323
- "content": "50",
324
  "single_word": false,
325
  "lstrip": false,
326
  "rstrip": false,
@@ -329,7 +329,7 @@
329
  },
330
  {
331
  "id": 36,
332
- "content": "99",
333
  "single_word": false,
334
  "lstrip": false,
335
  "rstrip": false,
@@ -338,7 +338,7 @@
338
  },
339
  {
340
  "id": 37,
341
- "content": "79",
342
  "single_word": false,
343
  "lstrip": false,
344
  "rstrip": false,
@@ -347,7 +347,7 @@
347
  },
348
  {
349
  "id": 38,
350
- "content": "16",
351
  "single_word": false,
352
  "lstrip": false,
353
  "rstrip": false,
@@ -356,7 +356,7 @@
356
  },
357
  {
358
  "id": 39,
359
- "content": "57",
360
  "single_word": false,
361
  "lstrip": false,
362
  "rstrip": false,
@@ -365,7 +365,7 @@
365
  },
366
  {
367
  "id": 40,
368
- "content": "26",
369
  "single_word": false,
370
  "lstrip": false,
371
  "rstrip": false,
@@ -374,7 +374,7 @@
374
  },
375
  {
376
  "id": 41,
377
- "content": "49",
378
  "single_word": false,
379
  "lstrip": false,
380
  "rstrip": false,
@@ -383,7 +383,7 @@
383
  },
384
  {
385
  "id": 42,
386
- "content": "68",
387
  "single_word": false,
388
  "lstrip": false,
389
  "rstrip": false,
@@ -392,7 +392,7 @@
392
  },
393
  {
394
  "id": 43,
395
- "content": "69",
396
  "single_word": false,
397
  "lstrip": false,
398
  "rstrip": false,
@@ -401,7 +401,7 @@
401
  },
402
  {
403
  "id": 44,
404
- "content": "85",
405
  "single_word": false,
406
  "lstrip": false,
407
  "rstrip": false,
@@ -410,7 +410,7 @@
410
  },
411
  {
412
  "id": 45,
413
- "content": "39",
414
  "single_word": false,
415
  "lstrip": false,
416
  "rstrip": false,
@@ -419,7 +419,7 @@
419
  },
420
  {
421
  "id": 46,
422
- "content": "45",
423
  "single_word": false,
424
  "lstrip": false,
425
  "rstrip": false,
@@ -428,7 +428,7 @@
428
  },
429
  {
430
  "id": 47,
431
- "content": "14",
432
  "single_word": false,
433
  "lstrip": false,
434
  "rstrip": false,
@@ -437,7 +437,7 @@
437
  },
438
  {
439
  "id": 48,
440
- "content": "59",
441
  "single_word": false,
442
  "lstrip": false,
443
  "rstrip": false,
@@ -446,7 +446,7 @@
446
  },
447
  {
448
  "id": 49,
449
- "content": "97",
450
  "single_word": false,
451
  "lstrip": false,
452
  "rstrip": false,
@@ -455,7 +455,7 @@
455
  },
456
  {
457
  "id": 50,
458
- "content": "62",
459
  "single_word": false,
460
  "lstrip": false,
461
  "rstrip": false,
@@ -464,7 +464,7 @@
464
  },
465
  {
466
  "id": 51,
467
- "content": "53",
468
  "single_word": false,
469
  "lstrip": false,
470
  "rstrip": false,
@@ -473,7 +473,7 @@
473
  },
474
  {
475
  "id": 52,
476
- "content": "15",
477
  "single_word": false,
478
  "lstrip": false,
479
  "rstrip": false,
@@ -482,7 +482,7 @@
482
  },
483
  {
484
  "id": 53,
485
- "content": "19",
486
  "single_word": false,
487
  "lstrip": false,
488
  "rstrip": false,
@@ -491,7 +491,7 @@
491
  },
492
  {
493
  "id": 54,
494
- "content": "37",
495
  "single_word": false,
496
  "lstrip": false,
497
  "rstrip": false,
@@ -500,7 +500,7 @@
500
  },
501
  {
502
  "id": 55,
503
- "content": "77",
504
  "single_word": false,
505
  "lstrip": false,
506
  "rstrip": false,
@@ -509,7 +509,7 @@
509
  },
510
  {
511
  "id": 56,
512
- "content": "95",
513
  "single_word": false,
514
  "lstrip": false,
515
  "rstrip": false,
@@ -518,7 +518,7 @@
518
  },
519
  {
520
  "id": 57,
521
- "content": "6",
522
  "single_word": false,
523
  "lstrip": false,
524
  "rstrip": false,
@@ -527,7 +527,7 @@
527
  },
528
  {
529
  "id": 58,
530
- "content": "78",
531
  "single_word": false,
532
  "lstrip": false,
533
  "rstrip": false,
@@ -536,7 +536,7 @@
536
  },
537
  {
538
  "id": 59,
539
- "content": "8",
540
  "single_word": false,
541
  "lstrip": false,
542
  "rstrip": false,
@@ -545,7 +545,7 @@
545
  },
546
  {
547
  "id": 60,
548
- "content": "24",
549
  "single_word": false,
550
  "lstrip": false,
551
  "rstrip": false,
@@ -554,7 +554,7 @@
554
  },
555
  {
556
  "id": 61,
557
- "content": "65",
558
  "single_word": false,
559
  "lstrip": false,
560
  "rstrip": false,
@@ -563,7 +563,7 @@
563
  },
564
  {
565
  "id": 62,
566
- "content": "67",
567
  "single_word": false,
568
  "lstrip": false,
569
  "rstrip": false,
@@ -572,7 +572,7 @@
572
  },
573
  {
574
  "id": 63,
575
- "content": "51",
576
  "single_word": false,
577
  "lstrip": false,
578
  "rstrip": false,
@@ -581,7 +581,7 @@
581
  },
582
  {
583
  "id": 64,
584
- "content": "75",
585
  "single_word": false,
586
  "lstrip": false,
587
  "rstrip": false,
@@ -590,7 +590,7 @@
590
  },
591
  {
592
  "id": 65,
593
- "content": "12",
594
  "single_word": false,
595
  "lstrip": false,
596
  "rstrip": false,
@@ -599,7 +599,7 @@
599
  },
600
  {
601
  "id": 66,
602
- "content": "47",
603
  "single_word": false,
604
  "lstrip": false,
605
  "rstrip": false,
@@ -608,7 +608,7 @@
608
  },
609
  {
610
  "id": 67,
611
- "content": "86",
612
  "single_word": false,
613
  "lstrip": false,
614
  "rstrip": false,
@@ -617,7 +617,7 @@
617
  },
618
  {
619
  "id": 68,
620
- "content": "7",
621
  "single_word": false,
622
  "lstrip": false,
623
  "rstrip": false,
@@ -626,7 +626,7 @@
626
  },
627
  {
628
  "id": 69,
629
- "content": "60",
630
  "single_word": false,
631
  "lstrip": false,
632
  "rstrip": false,
@@ -635,7 +635,7 @@
635
  },
636
  {
637
  "id": 70,
638
- "content": "23",
639
  "single_word": false,
640
  "lstrip": false,
641
  "rstrip": false,
@@ -644,7 +644,7 @@
644
  },
645
  {
646
  "id": 71,
647
- "content": "48",
648
  "single_word": false,
649
  "lstrip": false,
650
  "rstrip": false,
@@ -653,7 +653,7 @@
653
  },
654
  {
655
  "id": 72,
656
- "content": "30",
657
  "single_word": false,
658
  "lstrip": false,
659
  "rstrip": false,
@@ -662,7 +662,7 @@
662
  },
663
  {
664
  "id": 73,
665
- "content": "73",
666
  "single_word": false,
667
  "lstrip": false,
668
  "rstrip": false,
@@ -671,7 +671,7 @@
671
  },
672
  {
673
  "id": 74,
674
- "content": "34",
675
  "single_word": false,
676
  "lstrip": false,
677
  "rstrip": false,
@@ -680,7 +680,7 @@
680
  },
681
  {
682
  "id": 75,
683
- "content": "13",
684
  "single_word": false,
685
  "lstrip": false,
686
  "rstrip": false,
@@ -689,7 +689,7 @@
689
  },
690
  {
691
  "id": 76,
692
- "content": "52",
693
  "single_word": false,
694
  "lstrip": false,
695
  "rstrip": false,
@@ -698,7 +698,7 @@
698
  },
699
  {
700
  "id": 77,
701
- "content": "40",
702
  "single_word": false,
703
  "lstrip": false,
704
  "rstrip": false,
@@ -707,7 +707,7 @@
707
  },
708
  {
709
  "id": 78,
710
- "content": "56",
711
  "single_word": false,
712
  "lstrip": false,
713
  "rstrip": false,
@@ -716,7 +716,7 @@
716
  },
717
  {
718
  "id": 79,
719
- "content": "91",
720
  "single_word": false,
721
  "lstrip": false,
722
  "rstrip": false,
@@ -725,7 +725,7 @@
725
  },
726
  {
727
  "id": 80,
728
- "content": "71",
729
  "single_word": false,
730
  "lstrip": false,
731
  "rstrip": false,
@@ -734,7 +734,7 @@
734
  },
735
  {
736
  "id": 81,
737
- "content": "46",
738
  "single_word": false,
739
  "lstrip": false,
740
  "rstrip": false,
@@ -743,7 +743,7 @@
743
  },
744
  {
745
  "id": 82,
746
- "content": "92",
747
  "single_word": false,
748
  "lstrip": false,
749
  "rstrip": false,
@@ -752,7 +752,7 @@
752
  },
753
  {
754
  "id": 83,
755
- "content": "4",
756
  "single_word": false,
757
  "lstrip": false,
758
  "rstrip": false,
@@ -761,7 +761,7 @@
761
  },
762
  {
763
  "id": 84,
764
- "content": "32",
765
  "single_word": false,
766
  "lstrip": false,
767
  "rstrip": false,
@@ -770,7 +770,7 @@
770
  },
771
  {
772
  "id": 85,
773
- "content": "20",
774
  "single_word": false,
775
  "lstrip": false,
776
  "rstrip": false,
@@ -779,7 +779,7 @@
779
  },
780
  {
781
  "id": 86,
782
- "content": "25",
783
  "single_word": false,
784
  "lstrip": false,
785
  "rstrip": false,
@@ -788,7 +788,7 @@
788
  },
789
  {
790
  "id": 87,
791
- "content": "80",
792
  "single_word": false,
793
  "lstrip": false,
794
  "rstrip": false,
@@ -797,7 +797,7 @@
797
  },
798
  {
799
  "id": 88,
800
- "content": "22",
801
  "single_word": false,
802
  "lstrip": false,
803
  "rstrip": false,
@@ -806,7 +806,7 @@
806
  },
807
  {
808
  "id": 89,
809
- "content": "66",
810
  "single_word": false,
811
  "lstrip": false,
812
  "rstrip": false,
@@ -815,7 +815,7 @@
815
  },
816
  {
817
  "id": 90,
818
- "content": "1",
819
  "single_word": false,
820
  "lstrip": false,
821
  "rstrip": false,
@@ -824,7 +824,7 @@
824
  },
825
  {
826
  "id": 91,
827
- "content": "70",
828
  "single_word": false,
829
  "lstrip": false,
830
  "rstrip": false,
@@ -833,7 +833,7 @@
833
  },
834
  {
835
  "id": 92,
836
- "content": "88",
837
  "single_word": false,
838
  "lstrip": false,
839
  "rstrip": false,
@@ -842,7 +842,7 @@
842
  },
843
  {
844
  "id": 93,
845
- "content": "96",
846
  "single_word": false,
847
  "lstrip": false,
848
  "rstrip": false,
@@ -851,7 +851,7 @@
851
  },
852
  {
853
  "id": 94,
854
- "content": "41",
855
  "single_word": false,
856
  "lstrip": false,
857
  "rstrip": false,
@@ -860,7 +860,7 @@
860
  },
861
  {
862
  "id": 95,
863
- "content": "93",
864
  "single_word": false,
865
  "lstrip": false,
866
  "rstrip": false,
@@ -869,7 +869,7 @@
869
  },
870
  {
871
  "id": 96,
872
- "content": "84",
873
  "single_word": false,
874
  "lstrip": false,
875
  "rstrip": false,
@@ -878,7 +878,7 @@
878
  },
879
  {
880
  "id": 97,
881
- "content": "44",
882
  "single_word": false,
883
  "lstrip": false,
884
  "rstrip": false,
@@ -887,7 +887,7 @@
887
  },
888
  {
889
  "id": 98,
890
- "content": "82",
891
  "single_word": false,
892
  "lstrip": false,
893
  "rstrip": false,
@@ -896,7 +896,7 @@
896
  },
897
  {
898
  "id": 99,
899
- "content": "43",
900
  "single_word": false,
901
  "lstrip": false,
902
  "rstrip": false,
 
68
  },
69
  {
70
  "id": 7,
71
+ "content": "10",
72
  "single_word": false,
73
  "lstrip": false,
74
  "rstrip": false,
 
86
  },
87
  {
88
  "id": 9,
89
+ "content": "2",
90
  "single_word": false,
91
  "lstrip": false,
92
  "rstrip": false,
 
95
  },
96
  {
97
  "id": 10,
98
+ "content": "78",
99
  "single_word": false,
100
  "lstrip": false,
101
  "rstrip": false,
 
104
  },
105
  {
106
  "id": 11,
107
+ "content": "6",
108
  "single_word": false,
109
  "lstrip": false,
110
  "rstrip": false,
 
113
  },
114
  {
115
  "id": 12,
116
+ "content": "11",
117
  "single_word": false,
118
  "lstrip": false,
119
  "rstrip": false,
 
122
  },
123
  {
124
  "id": 13,
125
+ "content": "7",
126
  "single_word": false,
127
  "lstrip": false,
128
  "rstrip": false,
 
131
  },
132
  {
133
  "id": 14,
134
+ "content": "91",
135
  "single_word": false,
136
  "lstrip": false,
137
  "rstrip": false,
 
140
  },
141
  {
142
  "id": 15,
143
+ "content": "48",
144
  "single_word": false,
145
  "lstrip": false,
146
  "rstrip": false,
 
149
  },
150
  {
151
  "id": 16,
152
+ "content": "37",
153
  "single_word": false,
154
  "lstrip": false,
155
  "rstrip": false,
 
158
  },
159
  {
160
  "id": 17,
161
+ "content": "60",
162
  "single_word": false,
163
  "lstrip": false,
164
  "rstrip": false,
 
167
  },
168
  {
169
  "id": 18,
170
+ "content": "57",
171
  "single_word": false,
172
  "lstrip": false,
173
  "rstrip": false,
 
176
  },
177
  {
178
  "id": 19,
179
+ "content": "44",
180
  "single_word": false,
181
  "lstrip": false,
182
  "rstrip": false,
 
185
  },
186
  {
187
  "id": 20,
188
+ "content": "96",
189
  "single_word": false,
190
  "lstrip": false,
191
  "rstrip": false,
 
194
  },
195
  {
196
  "id": 21,
197
+ "content": "69",
198
  "single_word": false,
199
  "lstrip": false,
200
  "rstrip": false,
 
203
  },
204
  {
205
  "id": 22,
206
+ "content": "80",
207
  "single_word": false,
208
  "lstrip": false,
209
  "rstrip": false,
 
212
  },
213
  {
214
  "id": 23,
215
+ "content": "61",
216
  "single_word": false,
217
  "lstrip": false,
218
  "rstrip": false,
 
221
  },
222
  {
223
  "id": 24,
224
+ "content": "13",
225
  "single_word": false,
226
  "lstrip": false,
227
  "rstrip": false,
 
230
  },
231
  {
232
  "id": 25,
233
+ "content": "55",
234
  "single_word": false,
235
  "lstrip": false,
236
  "rstrip": false,
 
239
  },
240
  {
241
  "id": 26,
242
+ "content": "8",
243
  "single_word": false,
244
  "lstrip": false,
245
  "rstrip": false,
 
248
  },
249
  {
250
  "id": 27,
251
+ "content": "51",
252
  "single_word": false,
253
  "lstrip": false,
254
  "rstrip": false,
 
257
  },
258
  {
259
  "id": 28,
260
+ "content": "41",
261
  "single_word": false,
262
  "lstrip": false,
263
  "rstrip": false,
 
266
  },
267
  {
268
  "id": 29,
269
+ "content": "18",
270
  "single_word": false,
271
  "lstrip": false,
272
  "rstrip": false,
 
275
  },
276
  {
277
  "id": 30,
278
+ "content": "25",
279
  "single_word": false,
280
  "lstrip": false,
281
  "rstrip": false,
 
284
  },
285
  {
286
  "id": 31,
287
+ "content": "33",
288
  "single_word": false,
289
  "lstrip": false,
290
  "rstrip": false,
 
293
  },
294
  {
295
  "id": 32,
296
+ "content": "82",
297
  "single_word": false,
298
  "lstrip": false,
299
  "rstrip": false,
 
302
  },
303
  {
304
  "id": 33,
305
+ "content": "85",
306
  "single_word": false,
307
  "lstrip": false,
308
  "rstrip": false,
 
311
  },
312
  {
313
  "id": 34,
314
+ "content": "54",
315
  "single_word": false,
316
  "lstrip": false,
317
  "rstrip": false,
 
320
  },
321
  {
322
  "id": 35,
323
+ "content": "81",
324
  "single_word": false,
325
  "lstrip": false,
326
  "rstrip": false,
 
329
  },
330
  {
331
  "id": 36,
332
+ "content": "65",
333
  "single_word": false,
334
  "lstrip": false,
335
  "rstrip": false,
 
338
  },
339
  {
340
  "id": 37,
341
+ "content": "34",
342
  "single_word": false,
343
  "lstrip": false,
344
  "rstrip": false,
 
347
  },
348
  {
349
  "id": 38,
350
+ "content": "58",
351
  "single_word": false,
352
  "lstrip": false,
353
  "rstrip": false,
 
356
  },
357
  {
358
  "id": 39,
359
+ "content": "21",
360
  "single_word": false,
361
  "lstrip": false,
362
  "rstrip": false,
 
365
  },
366
  {
367
  "id": 40,
368
+ "content": "32",
369
  "single_word": false,
370
  "lstrip": false,
371
  "rstrip": false,
 
374
  },
375
  {
376
  "id": 41,
377
+ "content": "4",
378
  "single_word": false,
379
  "lstrip": false,
380
  "rstrip": false,
 
383
  },
384
  {
385
  "id": 42,
386
+ "content": "39",
387
  "single_word": false,
388
  "lstrip": false,
389
  "rstrip": false,
 
392
  },
393
  {
394
  "id": 43,
395
+ "content": "98",
396
  "single_word": false,
397
  "lstrip": false,
398
  "rstrip": false,
 
401
  },
402
  {
403
  "id": 44,
404
+ "content": "26",
405
  "single_word": false,
406
  "lstrip": false,
407
  "rstrip": false,
 
410
  },
411
  {
412
  "id": 45,
413
+ "content": "31",
414
  "single_word": false,
415
  "lstrip": false,
416
  "rstrip": false,
 
419
  },
420
  {
421
  "id": 46,
422
+ "content": "36",
423
  "single_word": false,
424
  "lstrip": false,
425
  "rstrip": false,
 
428
  },
429
  {
430
  "id": 47,
431
+ "content": "92",
432
  "single_word": false,
433
  "lstrip": false,
434
  "rstrip": false,
 
437
  },
438
  {
439
  "id": 48,
440
+ "content": "84",
441
  "single_word": false,
442
  "lstrip": false,
443
  "rstrip": false,
 
446
  },
447
  {
448
  "id": 49,
449
+ "content": "99",
450
  "single_word": false,
451
  "lstrip": false,
452
  "rstrip": false,
 
455
  },
456
  {
457
  "id": 50,
458
+ "content": "19",
459
  "single_word": false,
460
  "lstrip": false,
461
  "rstrip": false,
 
464
  },
465
  {
466
  "id": 51,
467
+ "content": "64",
468
  "single_word": false,
469
  "lstrip": false,
470
  "rstrip": false,
 
473
  },
474
  {
475
  "id": 52,
476
+ "content": "73",
477
  "single_word": false,
478
  "lstrip": false,
479
  "rstrip": false,
 
482
  },
483
  {
484
  "id": 53,
485
+ "content": "14",
486
  "single_word": false,
487
  "lstrip": false,
488
  "rstrip": false,
 
491
  },
492
  {
493
  "id": 54,
494
+ "content": "42",
495
  "single_word": false,
496
  "lstrip": false,
497
  "rstrip": false,
 
500
  },
501
  {
502
  "id": 55,
503
+ "content": "38",
504
  "single_word": false,
505
  "lstrip": false,
506
  "rstrip": false,
 
509
  },
510
  {
511
  "id": 56,
512
+ "content": "79",
513
  "single_word": false,
514
  "lstrip": false,
515
  "rstrip": false,
 
518
  },
519
  {
520
  "id": 57,
521
+ "content": "87",
522
  "single_word": false,
523
  "lstrip": false,
524
  "rstrip": false,
 
527
  },
528
  {
529
  "id": 58,
530
+ "content": "30",
531
  "single_word": false,
532
  "lstrip": false,
533
  "rstrip": false,
 
536
  },
537
  {
538
  "id": 59,
539
+ "content": "94",
540
  "single_word": false,
541
  "lstrip": false,
542
  "rstrip": false,
 
545
  },
546
  {
547
  "id": 60,
548
+ "content": "12",
549
  "single_word": false,
550
  "lstrip": false,
551
  "rstrip": false,
 
554
  },
555
  {
556
  "id": 61,
557
+ "content": "15",
558
  "single_word": false,
559
  "lstrip": false,
560
  "rstrip": false,
 
563
  },
564
  {
565
  "id": 62,
566
+ "content": "9",
567
  "single_word": false,
568
  "lstrip": false,
569
  "rstrip": false,
 
572
  },
573
  {
574
  "id": 63,
575
+ "content": "23",
576
  "single_word": false,
577
  "lstrip": false,
578
  "rstrip": false,
 
581
  },
582
  {
583
  "id": 64,
584
+ "content": "70",
585
  "single_word": false,
586
  "lstrip": false,
587
  "rstrip": false,
 
590
  },
591
  {
592
  "id": 65,
593
+ "content": "77",
594
  "single_word": false,
595
  "lstrip": false,
596
  "rstrip": false,
 
599
  },
600
  {
601
  "id": 66,
602
+ "content": "74",
603
  "single_word": false,
604
  "lstrip": false,
605
  "rstrip": false,
 
608
  },
609
  {
610
  "id": 67,
611
+ "content": "75",
612
  "single_word": false,
613
  "lstrip": false,
614
  "rstrip": false,
 
617
  },
618
  {
619
  "id": 68,
620
+ "content": "67",
621
  "single_word": false,
622
  "lstrip": false,
623
  "rstrip": false,
 
626
  },
627
  {
628
  "id": 69,
629
+ "content": "45",
630
  "single_word": false,
631
  "lstrip": false,
632
  "rstrip": false,
 
635
  },
636
  {
637
  "id": 70,
638
+ "content": "83",
639
  "single_word": false,
640
  "lstrip": false,
641
  "rstrip": false,
 
644
  },
645
  {
646
  "id": 71,
647
+ "content": "63",
648
  "single_word": false,
649
  "lstrip": false,
650
  "rstrip": false,
 
653
  },
654
  {
655
  "id": 72,
656
+ "content": "40",
657
  "single_word": false,
658
  "lstrip": false,
659
  "rstrip": false,
 
662
  },
663
  {
664
  "id": 73,
665
+ "content": "22",
666
  "single_word": false,
667
  "lstrip": false,
668
  "rstrip": false,
 
671
  },
672
  {
673
  "id": 74,
674
+ "content": "97",
675
  "single_word": false,
676
  "lstrip": false,
677
  "rstrip": false,
 
680
  },
681
  {
682
  "id": 75,
683
+ "content": "29",
684
  "single_word": false,
685
  "lstrip": false,
686
  "rstrip": false,
 
689
  },
690
  {
691
  "id": 76,
692
+ "content": "24",
693
  "single_word": false,
694
  "lstrip": false,
695
  "rstrip": false,
 
698
  },
699
  {
700
  "id": 77,
701
+ "content": "49",
702
  "single_word": false,
703
  "lstrip": false,
704
  "rstrip": false,
 
707
  },
708
  {
709
  "id": 78,
710
+ "content": "46",
711
  "single_word": false,
712
  "lstrip": false,
713
  "rstrip": false,
 
716
  },
717
  {
718
  "id": 79,
719
+ "content": "35",
720
  "single_word": false,
721
  "lstrip": false,
722
  "rstrip": false,
 
725
  },
726
  {
727
  "id": 80,
728
+ "content": "88",
729
  "single_word": false,
730
  "lstrip": false,
731
  "rstrip": false,
 
734
  },
735
  {
736
  "id": 81,
737
+ "content": "27",
738
  "single_word": false,
739
  "lstrip": false,
740
  "rstrip": false,
 
743
  },
744
  {
745
  "id": 82,
746
+ "content": "95",
747
  "single_word": false,
748
  "lstrip": false,
749
  "rstrip": false,
 
752
  },
753
  {
754
  "id": 83,
755
+ "content": "1",
756
  "single_word": false,
757
  "lstrip": false,
758
  "rstrip": false,
 
761
  },
762
  {
763
  "id": 84,
764
+ "content": "62",
765
  "single_word": false,
766
  "lstrip": false,
767
  "rstrip": false,
 
770
  },
771
  {
772
  "id": 85,
773
+ "content": "76",
774
  "single_word": false,
775
  "lstrip": false,
776
  "rstrip": false,
 
779
  },
780
  {
781
  "id": 86,
782
+ "content": "56",
783
  "single_word": false,
784
  "lstrip": false,
785
  "rstrip": false,
 
788
  },
789
  {
790
  "id": 87,
791
+ "content": "90",
792
  "single_word": false,
793
  "lstrip": false,
794
  "rstrip": false,
 
797
  },
798
  {
799
  "id": 88,
800
+ "content": "71",
801
  "single_word": false,
802
  "lstrip": false,
803
  "rstrip": false,
 
806
  },
807
  {
808
  "id": 89,
809
+ "content": "43",
810
  "single_word": false,
811
  "lstrip": false,
812
  "rstrip": false,
 
815
  },
816
  {
817
  "id": 90,
818
+ "content": "93",
819
  "single_word": false,
820
  "lstrip": false,
821
  "rstrip": false,
 
824
  },
825
  {
826
  "id": 91,
827
+ "content": "5",
828
  "single_word": false,
829
  "lstrip": false,
830
  "rstrip": false,
 
833
  },
834
  {
835
  "id": 92,
836
+ "content": "50",
837
  "single_word": false,
838
  "lstrip": false,
839
  "rstrip": false,
 
842
  },
843
  {
844
  "id": 93,
845
+ "content": "47",
846
  "single_word": false,
847
  "lstrip": false,
848
  "rstrip": false,
 
851
  },
852
  {
853
  "id": 94,
854
+ "content": "66",
855
  "single_word": false,
856
  "lstrip": false,
857
  "rstrip": false,
 
860
  },
861
  {
862
  "id": 95,
863
+ "content": "52",
864
  "single_word": false,
865
  "lstrip": false,
866
  "rstrip": false,
 
869
  },
870
  {
871
  "id": 96,
872
+ "content": "72",
873
  "single_word": false,
874
  "lstrip": false,
875
  "rstrip": false,
 
878
  },
879
  {
880
  "id": 97,
881
+ "content": "20",
882
  "single_word": false,
883
  "lstrip": false,
884
  "rstrip": false,
 
887
  },
888
  {
889
  "id": 98,
890
+ "content": "53",
891
  "single_word": false,
892
  "lstrip": false,
893
  "rstrip": false,
 
896
  },
897
  {
898
  "id": 99,
899
+ "content": "16",
900
  "single_word": false,
901
  "lstrip": false,
902
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -57,7 +57,7 @@
57
  "special": true
58
  },
59
  "7": {
60
- "content": "11",
61
  "lstrip": false,
62
  "normalized": true,
63
  "rstrip": false,
@@ -73,7 +73,7 @@
73
  "special": false
74
  },
75
  "9": {
76
- "content": "61",
77
  "lstrip": false,
78
  "normalized": true,
79
  "rstrip": false,
@@ -81,7 +81,7 @@
81
  "special": false
82
  },
83
  "10": {
84
- "content": "72",
85
  "lstrip": false,
86
  "normalized": true,
87
  "rstrip": false,
@@ -89,7 +89,7 @@
89
  "special": false
90
  },
91
  "11": {
92
- "content": "3",
93
  "lstrip": false,
94
  "normalized": true,
95
  "rstrip": false,
@@ -97,7 +97,7 @@
97
  "special": false
98
  },
99
  "12": {
100
- "content": "27",
101
  "lstrip": false,
102
  "normalized": true,
103
  "rstrip": false,
@@ -105,7 +105,7 @@
105
  "special": false
106
  },
107
  "13": {
108
- "content": "5",
109
  "lstrip": false,
110
  "normalized": true,
111
  "rstrip": false,
@@ -113,7 +113,7 @@
113
  "special": false
114
  },
115
  "14": {
116
- "content": "18",
117
  "lstrip": false,
118
  "normalized": true,
119
  "rstrip": false,
@@ -121,7 +121,7 @@
121
  "special": false
122
  },
123
  "15": {
124
- "content": "90",
125
  "lstrip": false,
126
  "normalized": true,
127
  "rstrip": false,
@@ -129,7 +129,7 @@
129
  "special": false
130
  },
131
  "16": {
132
- "content": "21",
133
  "lstrip": false,
134
  "normalized": true,
135
  "rstrip": false,
@@ -137,7 +137,7 @@
137
  "special": false
138
  },
139
  "17": {
140
- "content": "17",
141
  "lstrip": false,
142
  "normalized": true,
143
  "rstrip": false,
@@ -145,7 +145,7 @@
145
  "special": false
146
  },
147
  "18": {
148
- "content": "28",
149
  "lstrip": false,
150
  "normalized": true,
151
  "rstrip": false,
@@ -153,7 +153,7 @@
153
  "special": false
154
  },
155
  "19": {
156
- "content": "42",
157
  "lstrip": false,
158
  "normalized": true,
159
  "rstrip": false,
@@ -161,7 +161,7 @@
161
  "special": false
162
  },
163
  "20": {
164
- "content": "58",
165
  "lstrip": false,
166
  "normalized": true,
167
  "rstrip": false,
@@ -169,7 +169,7 @@
169
  "special": false
170
  },
171
  "21": {
172
- "content": "9",
173
  "lstrip": false,
174
  "normalized": true,
175
  "rstrip": false,
@@ -177,7 +177,7 @@
177
  "special": false
178
  },
179
  "22": {
180
- "content": "36",
181
  "lstrip": false,
182
  "normalized": true,
183
  "rstrip": false,
@@ -185,7 +185,7 @@
185
  "special": false
186
  },
187
  "23": {
188
- "content": "76",
189
  "lstrip": false,
190
  "normalized": true,
191
  "rstrip": false,
@@ -193,7 +193,7 @@
193
  "special": false
194
  },
195
  "24": {
196
- "content": "38",
197
  "lstrip": false,
198
  "normalized": true,
199
  "rstrip": false,
@@ -201,7 +201,7 @@
201
  "special": false
202
  },
203
  "25": {
204
- "content": "83",
205
  "lstrip": false,
206
  "normalized": true,
207
  "rstrip": false,
@@ -209,7 +209,7 @@
209
  "special": false
210
  },
211
  "26": {
212
- "content": "89",
213
  "lstrip": false,
214
  "normalized": true,
215
  "rstrip": false,
@@ -217,7 +217,7 @@
217
  "special": false
218
  },
219
  "27": {
220
- "content": "2",
221
  "lstrip": false,
222
  "normalized": true,
223
  "rstrip": false,
@@ -225,7 +225,7 @@
225
  "special": false
226
  },
227
  "28": {
228
- "content": "10",
229
  "lstrip": false,
230
  "normalized": true,
231
  "rstrip": false,
@@ -233,7 +233,7 @@
233
  "special": false
234
  },
235
  "29": {
236
- "content": "81",
237
  "lstrip": false,
238
  "normalized": true,
239
  "rstrip": false,
@@ -241,7 +241,7 @@
241
  "special": false
242
  },
243
  "30": {
244
- "content": "35",
245
  "lstrip": false,
246
  "normalized": true,
247
  "rstrip": false,
@@ -249,7 +249,7 @@
249
  "special": false
250
  },
251
  "31": {
252
- "content": "63",
253
  "lstrip": false,
254
  "normalized": true,
255
  "rstrip": false,
@@ -257,7 +257,7 @@
257
  "special": false
258
  },
259
  "32": {
260
- "content": "94",
261
  "lstrip": false,
262
  "normalized": true,
263
  "rstrip": false,
@@ -265,7 +265,7 @@
265
  "special": false
266
  },
267
  "33": {
268
- "content": "54",
269
  "lstrip": false,
270
  "normalized": true,
271
  "rstrip": false,
@@ -273,7 +273,7 @@
273
  "special": false
274
  },
275
  "34": {
276
- "content": "87",
277
  "lstrip": false,
278
  "normalized": true,
279
  "rstrip": false,
@@ -281,7 +281,7 @@
281
  "special": false
282
  },
283
  "35": {
284
- "content": "50",
285
  "lstrip": false,
286
  "normalized": true,
287
  "rstrip": false,
@@ -289,7 +289,7 @@
289
  "special": false
290
  },
291
  "36": {
292
- "content": "99",
293
  "lstrip": false,
294
  "normalized": true,
295
  "rstrip": false,
@@ -297,7 +297,7 @@
297
  "special": false
298
  },
299
  "37": {
300
- "content": "79",
301
  "lstrip": false,
302
  "normalized": true,
303
  "rstrip": false,
@@ -305,7 +305,7 @@
305
  "special": false
306
  },
307
  "38": {
308
- "content": "16",
309
  "lstrip": false,
310
  "normalized": true,
311
  "rstrip": false,
@@ -313,7 +313,7 @@
313
  "special": false
314
  },
315
  "39": {
316
- "content": "57",
317
  "lstrip": false,
318
  "normalized": true,
319
  "rstrip": false,
@@ -321,7 +321,7 @@
321
  "special": false
322
  },
323
  "40": {
324
- "content": "26",
325
  "lstrip": false,
326
  "normalized": true,
327
  "rstrip": false,
@@ -329,7 +329,7 @@
329
  "special": false
330
  },
331
  "41": {
332
- "content": "49",
333
  "lstrip": false,
334
  "normalized": true,
335
  "rstrip": false,
@@ -337,7 +337,7 @@
337
  "special": false
338
  },
339
  "42": {
340
- "content": "68",
341
  "lstrip": false,
342
  "normalized": true,
343
  "rstrip": false,
@@ -345,7 +345,7 @@
345
  "special": false
346
  },
347
  "43": {
348
- "content": "69",
349
  "lstrip": false,
350
  "normalized": true,
351
  "rstrip": false,
@@ -353,7 +353,7 @@
353
  "special": false
354
  },
355
  "44": {
356
- "content": "85",
357
  "lstrip": false,
358
  "normalized": true,
359
  "rstrip": false,
@@ -361,7 +361,7 @@
361
  "special": false
362
  },
363
  "45": {
364
- "content": "39",
365
  "lstrip": false,
366
  "normalized": true,
367
  "rstrip": false,
@@ -369,7 +369,7 @@
369
  "special": false
370
  },
371
  "46": {
372
- "content": "45",
373
  "lstrip": false,
374
  "normalized": true,
375
  "rstrip": false,
@@ -377,7 +377,7 @@
377
  "special": false
378
  },
379
  "47": {
380
- "content": "14",
381
  "lstrip": false,
382
  "normalized": true,
383
  "rstrip": false,
@@ -385,7 +385,7 @@
385
  "special": false
386
  },
387
  "48": {
388
- "content": "59",
389
  "lstrip": false,
390
  "normalized": true,
391
  "rstrip": false,
@@ -393,7 +393,7 @@
393
  "special": false
394
  },
395
  "49": {
396
- "content": "97",
397
  "lstrip": false,
398
  "normalized": true,
399
  "rstrip": false,
@@ -401,7 +401,7 @@
401
  "special": false
402
  },
403
  "50": {
404
- "content": "62",
405
  "lstrip": false,
406
  "normalized": true,
407
  "rstrip": false,
@@ -409,7 +409,7 @@
409
  "special": false
410
  },
411
  "51": {
412
- "content": "53",
413
  "lstrip": false,
414
  "normalized": true,
415
  "rstrip": false,
@@ -417,7 +417,7 @@
417
  "special": false
418
  },
419
  "52": {
420
- "content": "15",
421
  "lstrip": false,
422
  "normalized": true,
423
  "rstrip": false,
@@ -425,7 +425,7 @@
425
  "special": false
426
  },
427
  "53": {
428
- "content": "19",
429
  "lstrip": false,
430
  "normalized": true,
431
  "rstrip": false,
@@ -433,7 +433,7 @@
433
  "special": false
434
  },
435
  "54": {
436
- "content": "37",
437
  "lstrip": false,
438
  "normalized": true,
439
  "rstrip": false,
@@ -441,7 +441,7 @@
441
  "special": false
442
  },
443
  "55": {
444
- "content": "77",
445
  "lstrip": false,
446
  "normalized": true,
447
  "rstrip": false,
@@ -449,7 +449,7 @@
449
  "special": false
450
  },
451
  "56": {
452
- "content": "95",
453
  "lstrip": false,
454
  "normalized": true,
455
  "rstrip": false,
@@ -457,7 +457,7 @@
457
  "special": false
458
  },
459
  "57": {
460
- "content": "6",
461
  "lstrip": false,
462
  "normalized": true,
463
  "rstrip": false,
@@ -465,7 +465,7 @@
465
  "special": false
466
  },
467
  "58": {
468
- "content": "78",
469
  "lstrip": false,
470
  "normalized": true,
471
  "rstrip": false,
@@ -473,7 +473,7 @@
473
  "special": false
474
  },
475
  "59": {
476
- "content": "8",
477
  "lstrip": false,
478
  "normalized": true,
479
  "rstrip": false,
@@ -481,7 +481,7 @@
481
  "special": false
482
  },
483
  "60": {
484
- "content": "24",
485
  "lstrip": false,
486
  "normalized": true,
487
  "rstrip": false,
@@ -489,7 +489,7 @@
489
  "special": false
490
  },
491
  "61": {
492
- "content": "65",
493
  "lstrip": false,
494
  "normalized": true,
495
  "rstrip": false,
@@ -497,7 +497,7 @@
497
  "special": false
498
  },
499
  "62": {
500
- "content": "67",
501
  "lstrip": false,
502
  "normalized": true,
503
  "rstrip": false,
@@ -505,7 +505,7 @@
505
  "special": false
506
  },
507
  "63": {
508
- "content": "51",
509
  "lstrip": false,
510
  "normalized": true,
511
  "rstrip": false,
@@ -513,7 +513,7 @@
513
  "special": false
514
  },
515
  "64": {
516
- "content": "75",
517
  "lstrip": false,
518
  "normalized": true,
519
  "rstrip": false,
@@ -521,7 +521,7 @@
521
  "special": false
522
  },
523
  "65": {
524
- "content": "12",
525
  "lstrip": false,
526
  "normalized": true,
527
  "rstrip": false,
@@ -529,7 +529,7 @@
529
  "special": false
530
  },
531
  "66": {
532
- "content": "47",
533
  "lstrip": false,
534
  "normalized": true,
535
  "rstrip": false,
@@ -537,7 +537,7 @@
537
  "special": false
538
  },
539
  "67": {
540
- "content": "86",
541
  "lstrip": false,
542
  "normalized": true,
543
  "rstrip": false,
@@ -545,7 +545,7 @@
545
  "special": false
546
  },
547
  "68": {
548
- "content": "7",
549
  "lstrip": false,
550
  "normalized": true,
551
  "rstrip": false,
@@ -553,7 +553,7 @@
553
  "special": false
554
  },
555
  "69": {
556
- "content": "60",
557
  "lstrip": false,
558
  "normalized": true,
559
  "rstrip": false,
@@ -561,7 +561,7 @@
561
  "special": false
562
  },
563
  "70": {
564
- "content": "23",
565
  "lstrip": false,
566
  "normalized": true,
567
  "rstrip": false,
@@ -569,7 +569,7 @@
569
  "special": false
570
  },
571
  "71": {
572
- "content": "48",
573
  "lstrip": false,
574
  "normalized": true,
575
  "rstrip": false,
@@ -577,7 +577,7 @@
577
  "special": false
578
  },
579
  "72": {
580
- "content": "30",
581
  "lstrip": false,
582
  "normalized": true,
583
  "rstrip": false,
@@ -585,7 +585,7 @@
585
  "special": false
586
  },
587
  "73": {
588
- "content": "73",
589
  "lstrip": false,
590
  "normalized": true,
591
  "rstrip": false,
@@ -593,7 +593,7 @@
593
  "special": false
594
  },
595
  "74": {
596
- "content": "34",
597
  "lstrip": false,
598
  "normalized": true,
599
  "rstrip": false,
@@ -601,7 +601,7 @@
601
  "special": false
602
  },
603
  "75": {
604
- "content": "13",
605
  "lstrip": false,
606
  "normalized": true,
607
  "rstrip": false,
@@ -609,7 +609,7 @@
609
  "special": false
610
  },
611
  "76": {
612
- "content": "52",
613
  "lstrip": false,
614
  "normalized": true,
615
  "rstrip": false,
@@ -617,7 +617,7 @@
617
  "special": false
618
  },
619
  "77": {
620
- "content": "40",
621
  "lstrip": false,
622
  "normalized": true,
623
  "rstrip": false,
@@ -625,7 +625,7 @@
625
  "special": false
626
  },
627
  "78": {
628
- "content": "56",
629
  "lstrip": false,
630
  "normalized": true,
631
  "rstrip": false,
@@ -633,7 +633,7 @@
633
  "special": false
634
  },
635
  "79": {
636
- "content": "91",
637
  "lstrip": false,
638
  "normalized": true,
639
  "rstrip": false,
@@ -641,7 +641,7 @@
641
  "special": false
642
  },
643
  "80": {
644
- "content": "71",
645
  "lstrip": false,
646
  "normalized": true,
647
  "rstrip": false,
@@ -649,7 +649,7 @@
649
  "special": false
650
  },
651
  "81": {
652
- "content": "46",
653
  "lstrip": false,
654
  "normalized": true,
655
  "rstrip": false,
@@ -657,7 +657,7 @@
657
  "special": false
658
  },
659
  "82": {
660
- "content": "92",
661
  "lstrip": false,
662
  "normalized": true,
663
  "rstrip": false,
@@ -665,7 +665,7 @@
665
  "special": false
666
  },
667
  "83": {
668
- "content": "4",
669
  "lstrip": false,
670
  "normalized": true,
671
  "rstrip": false,
@@ -673,7 +673,7 @@
673
  "special": false
674
  },
675
  "84": {
676
- "content": "32",
677
  "lstrip": false,
678
  "normalized": true,
679
  "rstrip": false,
@@ -681,7 +681,7 @@
681
  "special": false
682
  },
683
  "85": {
684
- "content": "20",
685
  "lstrip": false,
686
  "normalized": true,
687
  "rstrip": false,
@@ -689,7 +689,7 @@
689
  "special": false
690
  },
691
  "86": {
692
- "content": "25",
693
  "lstrip": false,
694
  "normalized": true,
695
  "rstrip": false,
@@ -697,7 +697,7 @@
697
  "special": false
698
  },
699
  "87": {
700
- "content": "80",
701
  "lstrip": false,
702
  "normalized": true,
703
  "rstrip": false,
@@ -705,7 +705,7 @@
705
  "special": false
706
  },
707
  "88": {
708
- "content": "22",
709
  "lstrip": false,
710
  "normalized": true,
711
  "rstrip": false,
@@ -713,7 +713,7 @@
713
  "special": false
714
  },
715
  "89": {
716
- "content": "66",
717
  "lstrip": false,
718
  "normalized": true,
719
  "rstrip": false,
@@ -721,7 +721,7 @@
721
  "special": false
722
  },
723
  "90": {
724
- "content": "1",
725
  "lstrip": false,
726
  "normalized": true,
727
  "rstrip": false,
@@ -729,7 +729,7 @@
729
  "special": false
730
  },
731
  "91": {
732
- "content": "70",
733
  "lstrip": false,
734
  "normalized": true,
735
  "rstrip": false,
@@ -737,7 +737,7 @@
737
  "special": false
738
  },
739
  "92": {
740
- "content": "88",
741
  "lstrip": false,
742
  "normalized": true,
743
  "rstrip": false,
@@ -745,7 +745,7 @@
745
  "special": false
746
  },
747
  "93": {
748
- "content": "96",
749
  "lstrip": false,
750
  "normalized": true,
751
  "rstrip": false,
@@ -753,7 +753,7 @@
753
  "special": false
754
  },
755
  "94": {
756
- "content": "41",
757
  "lstrip": false,
758
  "normalized": true,
759
  "rstrip": false,
@@ -761,7 +761,7 @@
761
  "special": false
762
  },
763
  "95": {
764
- "content": "93",
765
  "lstrip": false,
766
  "normalized": true,
767
  "rstrip": false,
@@ -769,7 +769,7 @@
769
  "special": false
770
  },
771
  "96": {
772
- "content": "84",
773
  "lstrip": false,
774
  "normalized": true,
775
  "rstrip": false,
@@ -777,7 +777,7 @@
777
  "special": false
778
  },
779
  "97": {
780
- "content": "44",
781
  "lstrip": false,
782
  "normalized": true,
783
  "rstrip": false,
@@ -785,7 +785,7 @@
785
  "special": false
786
  },
787
  "98": {
788
- "content": "82",
789
  "lstrip": false,
790
  "normalized": true,
791
  "rstrip": false,
@@ -793,7 +793,7 @@
793
  "special": false
794
  },
795
  "99": {
796
- "content": "43",
797
  "lstrip": false,
798
  "normalized": true,
799
  "rstrip": false,
 
57
  "special": true
58
  },
59
  "7": {
60
+ "content": "10",
61
  "lstrip": false,
62
  "normalized": true,
63
  "rstrip": false,
 
73
  "special": false
74
  },
75
  "9": {
76
+ "content": "2",
77
  "lstrip": false,
78
  "normalized": true,
79
  "rstrip": false,
 
81
  "special": false
82
  },
83
  "10": {
84
+ "content": "78",
85
  "lstrip": false,
86
  "normalized": true,
87
  "rstrip": false,
 
89
  "special": false
90
  },
91
  "11": {
92
+ "content": "6",
93
  "lstrip": false,
94
  "normalized": true,
95
  "rstrip": false,
 
97
  "special": false
98
  },
99
  "12": {
100
+ "content": "11",
101
  "lstrip": false,
102
  "normalized": true,
103
  "rstrip": false,
 
105
  "special": false
106
  },
107
  "13": {
108
+ "content": "7",
109
  "lstrip": false,
110
  "normalized": true,
111
  "rstrip": false,
 
113
  "special": false
114
  },
115
  "14": {
116
+ "content": "91",
117
  "lstrip": false,
118
  "normalized": true,
119
  "rstrip": false,
 
121
  "special": false
122
  },
123
  "15": {
124
+ "content": "48",
125
  "lstrip": false,
126
  "normalized": true,
127
  "rstrip": false,
 
129
  "special": false
130
  },
131
  "16": {
132
+ "content": "37",
133
  "lstrip": false,
134
  "normalized": true,
135
  "rstrip": false,
 
137
  "special": false
138
  },
139
  "17": {
140
+ "content": "60",
141
  "lstrip": false,
142
  "normalized": true,
143
  "rstrip": false,
 
145
  "special": false
146
  },
147
  "18": {
148
+ "content": "57",
149
  "lstrip": false,
150
  "normalized": true,
151
  "rstrip": false,
 
153
  "special": false
154
  },
155
  "19": {
156
+ "content": "44",
157
  "lstrip": false,
158
  "normalized": true,
159
  "rstrip": false,
 
161
  "special": false
162
  },
163
  "20": {
164
+ "content": "96",
165
  "lstrip": false,
166
  "normalized": true,
167
  "rstrip": false,
 
169
  "special": false
170
  },
171
  "21": {
172
+ "content": "69",
173
  "lstrip": false,
174
  "normalized": true,
175
  "rstrip": false,
 
177
  "special": false
178
  },
179
  "22": {
180
+ "content": "80",
181
  "lstrip": false,
182
  "normalized": true,
183
  "rstrip": false,
 
185
  "special": false
186
  },
187
  "23": {
188
+ "content": "61",
189
  "lstrip": false,
190
  "normalized": true,
191
  "rstrip": false,
 
193
  "special": false
194
  },
195
  "24": {
196
+ "content": "13",
197
  "lstrip": false,
198
  "normalized": true,
199
  "rstrip": false,
 
201
  "special": false
202
  },
203
  "25": {
204
+ "content": "55",
205
  "lstrip": false,
206
  "normalized": true,
207
  "rstrip": false,
 
209
  "special": false
210
  },
211
  "26": {
212
+ "content": "8",
213
  "lstrip": false,
214
  "normalized": true,
215
  "rstrip": false,
 
217
  "special": false
218
  },
219
  "27": {
220
+ "content": "51",
221
  "lstrip": false,
222
  "normalized": true,
223
  "rstrip": false,
 
225
  "special": false
226
  },
227
  "28": {
228
+ "content": "41",
229
  "lstrip": false,
230
  "normalized": true,
231
  "rstrip": false,
 
233
  "special": false
234
  },
235
  "29": {
236
+ "content": "18",
237
  "lstrip": false,
238
  "normalized": true,
239
  "rstrip": false,
 
241
  "special": false
242
  },
243
  "30": {
244
+ "content": "25",
245
  "lstrip": false,
246
  "normalized": true,
247
  "rstrip": false,
 
249
  "special": false
250
  },
251
  "31": {
252
+ "content": "33",
253
  "lstrip": false,
254
  "normalized": true,
255
  "rstrip": false,
 
257
  "special": false
258
  },
259
  "32": {
260
+ "content": "82",
261
  "lstrip": false,
262
  "normalized": true,
263
  "rstrip": false,
 
265
  "special": false
266
  },
267
  "33": {
268
+ "content": "85",
269
  "lstrip": false,
270
  "normalized": true,
271
  "rstrip": false,
 
273
  "special": false
274
  },
275
  "34": {
276
+ "content": "54",
277
  "lstrip": false,
278
  "normalized": true,
279
  "rstrip": false,
 
281
  "special": false
282
  },
283
  "35": {
284
+ "content": "81",
285
  "lstrip": false,
286
  "normalized": true,
287
  "rstrip": false,
 
289
  "special": false
290
  },
291
  "36": {
292
+ "content": "65",
293
  "lstrip": false,
294
  "normalized": true,
295
  "rstrip": false,
 
297
  "special": false
298
  },
299
  "37": {
300
+ "content": "34",
301
  "lstrip": false,
302
  "normalized": true,
303
  "rstrip": false,
 
305
  "special": false
306
  },
307
  "38": {
308
+ "content": "58",
309
  "lstrip": false,
310
  "normalized": true,
311
  "rstrip": false,
 
313
  "special": false
314
  },
315
  "39": {
316
+ "content": "21",
317
  "lstrip": false,
318
  "normalized": true,
319
  "rstrip": false,
 
321
  "special": false
322
  },
323
  "40": {
324
+ "content": "32",
325
  "lstrip": false,
326
  "normalized": true,
327
  "rstrip": false,
 
329
  "special": false
330
  },
331
  "41": {
332
+ "content": "4",
333
  "lstrip": false,
334
  "normalized": true,
335
  "rstrip": false,
 
337
  "special": false
338
  },
339
  "42": {
340
+ "content": "39",
341
  "lstrip": false,
342
  "normalized": true,
343
  "rstrip": false,
 
345
  "special": false
346
  },
347
  "43": {
348
+ "content": "98",
349
  "lstrip": false,
350
  "normalized": true,
351
  "rstrip": false,
 
353
  "special": false
354
  },
355
  "44": {
356
+ "content": "26",
357
  "lstrip": false,
358
  "normalized": true,
359
  "rstrip": false,
 
361
  "special": false
362
  },
363
  "45": {
364
+ "content": "31",
365
  "lstrip": false,
366
  "normalized": true,
367
  "rstrip": false,
 
369
  "special": false
370
  },
371
  "46": {
372
+ "content": "36",
373
  "lstrip": false,
374
  "normalized": true,
375
  "rstrip": false,
 
377
  "special": false
378
  },
379
  "47": {
380
+ "content": "92",
381
  "lstrip": false,
382
  "normalized": true,
383
  "rstrip": false,
 
385
  "special": false
386
  },
387
  "48": {
388
+ "content": "84",
389
  "lstrip": false,
390
  "normalized": true,
391
  "rstrip": false,
 
393
  "special": false
394
  },
395
  "49": {
396
+ "content": "99",
397
  "lstrip": false,
398
  "normalized": true,
399
  "rstrip": false,
 
401
  "special": false
402
  },
403
  "50": {
404
+ "content": "19",
405
  "lstrip": false,
406
  "normalized": true,
407
  "rstrip": false,
 
409
  "special": false
410
  },
411
  "51": {
412
+ "content": "64",
413
  "lstrip": false,
414
  "normalized": true,
415
  "rstrip": false,
 
417
  "special": false
418
  },
419
  "52": {
420
+ "content": "73",
421
  "lstrip": false,
422
  "normalized": true,
423
  "rstrip": false,
 
425
  "special": false
426
  },
427
  "53": {
428
+ "content": "14",
429
  "lstrip": false,
430
  "normalized": true,
431
  "rstrip": false,
 
433
  "special": false
434
  },
435
  "54": {
436
+ "content": "42",
437
  "lstrip": false,
438
  "normalized": true,
439
  "rstrip": false,
 
441
  "special": false
442
  },
443
  "55": {
444
+ "content": "38",
445
  "lstrip": false,
446
  "normalized": true,
447
  "rstrip": false,
 
449
  "special": false
450
  },
451
  "56": {
452
+ "content": "79",
453
  "lstrip": false,
454
  "normalized": true,
455
  "rstrip": false,
 
457
  "special": false
458
  },
459
  "57": {
460
+ "content": "87",
461
  "lstrip": false,
462
  "normalized": true,
463
  "rstrip": false,
 
465
  "special": false
466
  },
467
  "58": {
468
+ "content": "30",
469
  "lstrip": false,
470
  "normalized": true,
471
  "rstrip": false,
 
473
  "special": false
474
  },
475
  "59": {
476
+ "content": "94",
477
  "lstrip": false,
478
  "normalized": true,
479
  "rstrip": false,
 
481
  "special": false
482
  },
483
  "60": {
484
+ "content": "12",
485
  "lstrip": false,
486
  "normalized": true,
487
  "rstrip": false,
 
489
  "special": false
490
  },
491
  "61": {
492
+ "content": "15",
493
  "lstrip": false,
494
  "normalized": true,
495
  "rstrip": false,
 
497
  "special": false
498
  },
499
  "62": {
500
+ "content": "9",
501
  "lstrip": false,
502
  "normalized": true,
503
  "rstrip": false,
 
505
  "special": false
506
  },
507
  "63": {
508
+ "content": "23",
509
  "lstrip": false,
510
  "normalized": true,
511
  "rstrip": false,
 
513
  "special": false
514
  },
515
  "64": {
516
+ "content": "70",
517
  "lstrip": false,
518
  "normalized": true,
519
  "rstrip": false,
 
521
  "special": false
522
  },
523
  "65": {
524
+ "content": "77",
525
  "lstrip": false,
526
  "normalized": true,
527
  "rstrip": false,
 
529
  "special": false
530
  },
531
  "66": {
532
+ "content": "74",
533
  "lstrip": false,
534
  "normalized": true,
535
  "rstrip": false,
 
537
  "special": false
538
  },
539
  "67": {
540
+ "content": "75",
541
  "lstrip": false,
542
  "normalized": true,
543
  "rstrip": false,
 
545
  "special": false
546
  },
547
  "68": {
548
+ "content": "67",
549
  "lstrip": false,
550
  "normalized": true,
551
  "rstrip": false,
 
553
  "special": false
554
  },
555
  "69": {
556
+ "content": "45",
557
  "lstrip": false,
558
  "normalized": true,
559
  "rstrip": false,
 
561
  "special": false
562
  },
563
  "70": {
564
+ "content": "83",
565
  "lstrip": false,
566
  "normalized": true,
567
  "rstrip": false,
 
569
  "special": false
570
  },
571
  "71": {
572
+ "content": "63",
573
  "lstrip": false,
574
  "normalized": true,
575
  "rstrip": false,
 
577
  "special": false
578
  },
579
  "72": {
580
+ "content": "40",
581
  "lstrip": false,
582
  "normalized": true,
583
  "rstrip": false,
 
585
  "special": false
586
  },
587
  "73": {
588
+ "content": "22",
589
  "lstrip": false,
590
  "normalized": true,
591
  "rstrip": false,
 
593
  "special": false
594
  },
595
  "74": {
596
+ "content": "97",
597
  "lstrip": false,
598
  "normalized": true,
599
  "rstrip": false,
 
601
  "special": false
602
  },
603
  "75": {
604
+ "content": "29",
605
  "lstrip": false,
606
  "normalized": true,
607
  "rstrip": false,
 
609
  "special": false
610
  },
611
  "76": {
612
+ "content": "24",
613
  "lstrip": false,
614
  "normalized": true,
615
  "rstrip": false,
 
617
  "special": false
618
  },
619
  "77": {
620
+ "content": "49",
621
  "lstrip": false,
622
  "normalized": true,
623
  "rstrip": false,
 
625
  "special": false
626
  },
627
  "78": {
628
+ "content": "46",
629
  "lstrip": false,
630
  "normalized": true,
631
  "rstrip": false,
 
633
  "special": false
634
  },
635
  "79": {
636
+ "content": "35",
637
  "lstrip": false,
638
  "normalized": true,
639
  "rstrip": false,
 
641
  "special": false
642
  },
643
  "80": {
644
+ "content": "88",
645
  "lstrip": false,
646
  "normalized": true,
647
  "rstrip": false,
 
649
  "special": false
650
  },
651
  "81": {
652
+ "content": "27",
653
  "lstrip": false,
654
  "normalized": true,
655
  "rstrip": false,
 
657
  "special": false
658
  },
659
  "82": {
660
+ "content": "95",
661
  "lstrip": false,
662
  "normalized": true,
663
  "rstrip": false,
 
665
  "special": false
666
  },
667
  "83": {
668
+ "content": "1",
669
  "lstrip": false,
670
  "normalized": true,
671
  "rstrip": false,
 
673
  "special": false
674
  },
675
  "84": {
676
+ "content": "62",
677
  "lstrip": false,
678
  "normalized": true,
679
  "rstrip": false,
 
681
  "special": false
682
  },
683
  "85": {
684
+ "content": "76",
685
  "lstrip": false,
686
  "normalized": true,
687
  "rstrip": false,
 
689
  "special": false
690
  },
691
  "86": {
692
+ "content": "56",
693
  "lstrip": false,
694
  "normalized": true,
695
  "rstrip": false,
 
697
  "special": false
698
  },
699
  "87": {
700
+ "content": "90",
701
  "lstrip": false,
702
  "normalized": true,
703
  "rstrip": false,
 
705
  "special": false
706
  },
707
  "88": {
708
+ "content": "71",
709
  "lstrip": false,
710
  "normalized": true,
711
  "rstrip": false,
 
713
  "special": false
714
  },
715
  "89": {
716
+ "content": "43",
717
  "lstrip": false,
718
  "normalized": true,
719
  "rstrip": false,
 
721
  "special": false
722
  },
723
  "90": {
724
+ "content": "93",
725
  "lstrip": false,
726
  "normalized": true,
727
  "rstrip": false,
 
729
  "special": false
730
  },
731
  "91": {
732
+ "content": "5",
733
  "lstrip": false,
734
  "normalized": true,
735
  "rstrip": false,
 
737
  "special": false
738
  },
739
  "92": {
740
+ "content": "50",
741
  "lstrip": false,
742
  "normalized": true,
743
  "rstrip": false,
 
745
  "special": false
746
  },
747
  "93": {
748
+ "content": "47",
749
  "lstrip": false,
750
  "normalized": true,
751
  "rstrip": false,
 
753
  "special": false
754
  },
755
  "94": {
756
+ "content": "66",
757
  "lstrip": false,
758
  "normalized": true,
759
  "rstrip": false,
 
761
  "special": false
762
  },
763
  "95": {
764
+ "content": "52",
765
  "lstrip": false,
766
  "normalized": true,
767
  "rstrip": false,
 
769
  "special": false
770
  },
771
  "96": {
772
+ "content": "72",
773
  "lstrip": false,
774
  "normalized": true,
775
  "rstrip": false,
 
777
  "special": false
778
  },
779
  "97": {
780
+ "content": "20",
781
  "lstrip": false,
782
  "normalized": true,
783
  "rstrip": false,
 
785
  "special": false
786
  },
787
  "98": {
788
+ "content": "53",
789
  "lstrip": false,
790
  "normalized": true,
791
  "rstrip": false,
 
793
  "special": false
794
  },
795
  "99": {
796
+ "content": "16",
797
  "lstrip": false,
798
  "normalized": true,
799
  "rstrip": false,
vocab.json CHANGED
@@ -1,109 +1,109 @@
1
  {
2
- "12": 65,
3
- "94": 32,
4
- "55": 0,
5
- "35": 30,
6
- "97": 49,
7
- "1": 90,
8
- "88": 92,
9
- "96": 93,
10
- "30": 72,
11
- "86": 67,
12
- "8": 59,
13
- "</s>": 2,
14
- "11": 7,
15
- "74": 5,
16
- "89": 26,
17
  "0": 8,
18
- "92": 82,
19
- "27": 12,
20
- "54": 33,
21
- "64": 4,
22
- "59": 48,
23
- "31": 2,
24
- "5": 13,
25
- "93": 95,
26
- "90": 15,
27
- "91": 79,
28
- "2": 27,
29
- "75": 64,
30
- "62": 50,
31
- "82": 98,
32
- "21": 16,
33
- "63": 31,
34
- "81": 29,
35
- "9": 21,
36
- " ": 6,
37
- "58": 20,
38
- "25": 86,
39
- "41": 94,
40
- "99": 36,
41
- "71": 80,
42
- "26": 40,
43
- "79": 37,
44
- "56": 78,
45
- "67": 62,
46
- "37": 54,
47
- "10": 28,
48
- "mod": 4,
49
- "48": 71,
50
- "57": 39,
51
- "13": 75,
52
- "33": 1,
53
- "7": 68,
54
- "85": 44,
55
- "42": 19,
56
- "98": 6,
57
- "70": 91,
58
- "49": 41,
59
- "36": 22,
60
- "83": 25,
61
- "<unk>": 0,
62
- "95": 56,
63
- "80": 87,
64
- "39": 45,
65
- "6": 57,
66
  "<pad>": 3,
67
- "29": 3,
68
- "45": 46,
69
- "22": 88,
70
- "14": 47,
71
- "34": 74,
72
- "15": 52,
73
- "17": 17,
74
- "23": 70,
75
- "38": 24,
76
- "60": 69,
77
- "16": 38,
78
- "61": 9,
79
- "87": 34,
80
- "32": 84,
81
- "28": 18,
82
- "4": 83,
83
- "18": 14,
84
- "24": 60,
85
- "69": 43,
86
- "43": 99,
87
- "73": 73,
88
- "72": 10,
89
- "44": 97,
90
- "68": 42,
91
- "40": 77,
92
- "78": 58,
 
93
  "=": 5,
94
- "77": 55,
95
- "47": 66,
96
- "3": 11,
97
- "52": 76,
98
- "46": 81,
99
- "20": 85,
100
- "65": 61,
101
- "84": 96,
102
- "51": 63,
103
- "76": 23,
104
- "53": 51,
105
- "50": 35,
106
- "19": 53,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
107
  "<s>": 1,
108
- "66": 89
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
109
  }
 
1
  {
2
+ "89": 2,
3
+ "13": 24,
4
+ "63": 71,
5
+ "59": 5,
6
+ "56": 86,
7
+ "48": 15,
8
+ "61": 23,
9
+ "62": 84,
10
+ "27": 81,
11
+ "91": 14,
12
+ "16": 99,
13
+ "17": 0,
14
+ "67": 68,
 
 
15
  "0": 8,
16
+ "93": 90,
17
+ "64": 51,
18
+ "77": 65,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  "<pad>": 3,
20
+ "28": 6,
21
+ "5": 91,
22
+ "55": 25,
23
+ "25": 30,
24
+ "21": 39,
25
+ "95": 82,
26
+ "84": 48,
27
+ "65": 36,
28
+ "73": 52,
29
+ "35": 79,
30
+ "31": 45,
31
+ "39": 42,
32
+ "37": 16,
33
+ "10": 7,
34
+ "24": 76,
35
+ "12": 60,
36
+ "2": 9,
37
+ "14": 53,
38
+ "92": 47,
39
+ "44": 19,
40
+ "43": 89,
41
+ "47": 93,
42
+ "79": 56,
43
+ "9": 62,
44
+ "45": 69,
45
+ "38": 55,
46
+ "23": 63,
47
  "=": 5,
48
+ "22": 73,
49
+ "66": 94,
50
+ "72": 96,
51
+ "7": 13,
52
+ "75": 67,
53
+ "3": 1,
54
+ "34": 37,
55
+ "82": 32,
56
+ "69": 21,
57
+ "30": 58,
58
+ "mod": 4,
59
+ "53": 98,
60
+ "15": 61,
61
+ "54": 34,
62
+ "49": 77,
63
+ "11": 12,
64
+ "29": 75,
65
+ "98": 43,
66
+ "8": 26,
67
+ "<unk>": 0,
68
+ "46": 78,
69
+ "58": 38,
70
+ "68": 4,
71
+ "18": 29,
72
+ "26": 44,
73
+ "97": 74,
74
+ "6": 11,
75
+ "36": 46,
76
+ "33": 31,
77
+ "81": 35,
78
+ "32": 40,
79
+ "85": 33,
80
+ "76": 85,
81
+ "52": 95,
82
  "<s>": 1,
83
+ "40": 72,
84
+ "94": 59,
85
+ "20": 97,
86
+ "1": 83,
87
+ "87": 57,
88
+ "71": 88,
89
+ " ": 6,
90
+ "78": 10,
91
+ "60": 17,
92
+ "88": 80,
93
+ "99": 49,
94
+ "80": 22,
95
+ "41": 28,
96
+ "42": 54,
97
+ "83": 70,
98
+ "50": 92,
99
+ "96": 20,
100
+ "74": 66,
101
+ "86": 3,
102
+ "57": 18,
103
+ "51": 27,
104
+ "70": 64,
105
+ "90": 87,
106
+ "</s>": 2,
107
+ "4": 41,
108
+ "19": 50
109
  }