gsaltintas commited on
Commit
3dd1eb9
·
verified ·
1 Parent(s): 9219f18

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. merges.txt +1 -0
  3. tokenizer.json +94 -1080
  4. tokenizer_config.json +0 -880
  5. vocab.json +100 -100
README.md CHANGED
@@ -46,4 +46,4 @@ tokens = tokenizer.encode("Hello, world!")
46
  ## Sample Encoding
47
  | Text | Tokens | Token IDs |
48
  |------|--------|-----------|
49
- | `123450019 mod 67` | `12, 34, 50, 0, 19, , mod, , 67` | `20, 42, 58, 7, 27, 6, 4, 6, 75` |
 
46
  ## Sample Encoding
47
  | Text | Tokens | Token IDs |
48
  |------|--------|-----------|
49
+ | `1234500119 mod 67` | `12, 34, 50, 0, 1, 19, , mod, , 67` | `19, 41, 57, 7, 8, 26, 6, 4, 6, 74` |
merges.txt CHANGED
@@ -88,3 +88,4 @@
88
  ['9', '6']
89
  ['9', '7']
90
  ['9', '8']
 
 
88
  ['9', '6']
89
  ['9', '7']
90
  ['9', '8']
91
+ ['9', '9']
tokenizer.json CHANGED
@@ -65,996 +65,6 @@
65
  "rstrip": false,
66
  "normalized": false,
67
  "special": true
68
- },
69
- {
70
- "id": 7,
71
- "content": "0",
72
- "single_word": false,
73
- "lstrip": false,
74
- "rstrip": false,
75
- "normalized": true,
76
- "special": false
77
- },
78
- {
79
- "id": 8,
80
- "content": "1",
81
- "single_word": false,
82
- "lstrip": false,
83
- "rstrip": false,
84
- "normalized": true,
85
- "special": false
86
- },
87
- {
88
- "id": 9,
89
- "content": "2",
90
- "single_word": false,
91
- "lstrip": false,
92
- "rstrip": false,
93
- "normalized": true,
94
- "special": false
95
- },
96
- {
97
- "id": 10,
98
- "content": "3",
99
- "single_word": false,
100
- "lstrip": false,
101
- "rstrip": false,
102
- "normalized": true,
103
- "special": false
104
- },
105
- {
106
- "id": 11,
107
- "content": "4",
108
- "single_word": false,
109
- "lstrip": false,
110
- "rstrip": false,
111
- "normalized": true,
112
- "special": false
113
- },
114
- {
115
- "id": 12,
116
- "content": "5",
117
- "single_word": false,
118
- "lstrip": false,
119
- "rstrip": false,
120
- "normalized": true,
121
- "special": false
122
- },
123
- {
124
- "id": 13,
125
- "content": "6",
126
- "single_word": false,
127
- "lstrip": false,
128
- "rstrip": false,
129
- "normalized": true,
130
- "special": false
131
- },
132
- {
133
- "id": 14,
134
- "content": "7",
135
- "single_word": false,
136
- "lstrip": false,
137
- "rstrip": false,
138
- "normalized": true,
139
- "special": false
140
- },
141
- {
142
- "id": 15,
143
- "content": "8",
144
- "single_word": false,
145
- "lstrip": false,
146
- "rstrip": false,
147
- "normalized": true,
148
- "special": false
149
- },
150
- {
151
- "id": 16,
152
- "content": "9",
153
- "single_word": false,
154
- "lstrip": false,
155
- "rstrip": false,
156
- "normalized": true,
157
- "special": false
158
- },
159
- {
160
- "id": 18,
161
- "content": "10",
162
- "single_word": false,
163
- "lstrip": false,
164
- "rstrip": false,
165
- "normalized": true,
166
- "special": false
167
- },
168
- {
169
- "id": 19,
170
- "content": "11",
171
- "single_word": false,
172
- "lstrip": false,
173
- "rstrip": false,
174
- "normalized": true,
175
- "special": false
176
- },
177
- {
178
- "id": 20,
179
- "content": "12",
180
- "single_word": false,
181
- "lstrip": false,
182
- "rstrip": false,
183
- "normalized": true,
184
- "special": false
185
- },
186
- {
187
- "id": 21,
188
- "content": "13",
189
- "single_word": false,
190
- "lstrip": false,
191
- "rstrip": false,
192
- "normalized": true,
193
- "special": false
194
- },
195
- {
196
- "id": 22,
197
- "content": "14",
198
- "single_word": false,
199
- "lstrip": false,
200
- "rstrip": false,
201
- "normalized": true,
202
- "special": false
203
- },
204
- {
205
- "id": 23,
206
- "content": "15",
207
- "single_word": false,
208
- "lstrip": false,
209
- "rstrip": false,
210
- "normalized": true,
211
- "special": false
212
- },
213
- {
214
- "id": 24,
215
- "content": "16",
216
- "single_word": false,
217
- "lstrip": false,
218
- "rstrip": false,
219
- "normalized": true,
220
- "special": false
221
- },
222
- {
223
- "id": 25,
224
- "content": "17",
225
- "single_word": false,
226
- "lstrip": false,
227
- "rstrip": false,
228
- "normalized": true,
229
- "special": false
230
- },
231
- {
232
- "id": 26,
233
- "content": "18",
234
- "single_word": false,
235
- "lstrip": false,
236
- "rstrip": false,
237
- "normalized": true,
238
- "special": false
239
- },
240
- {
241
- "id": 27,
242
- "content": "19",
243
- "single_word": false,
244
- "lstrip": false,
245
- "rstrip": false,
246
- "normalized": true,
247
- "special": false
248
- },
249
- {
250
- "id": 28,
251
- "content": "20",
252
- "single_word": false,
253
- "lstrip": false,
254
- "rstrip": false,
255
- "normalized": true,
256
- "special": false
257
- },
258
- {
259
- "id": 29,
260
- "content": "21",
261
- "single_word": false,
262
- "lstrip": false,
263
- "rstrip": false,
264
- "normalized": true,
265
- "special": false
266
- },
267
- {
268
- "id": 30,
269
- "content": "22",
270
- "single_word": false,
271
- "lstrip": false,
272
- "rstrip": false,
273
- "normalized": true,
274
- "special": false
275
- },
276
- {
277
- "id": 31,
278
- "content": "23",
279
- "single_word": false,
280
- "lstrip": false,
281
- "rstrip": false,
282
- "normalized": true,
283
- "special": false
284
- },
285
- {
286
- "id": 32,
287
- "content": "24",
288
- "single_word": false,
289
- "lstrip": false,
290
- "rstrip": false,
291
- "normalized": true,
292
- "special": false
293
- },
294
- {
295
- "id": 33,
296
- "content": "25",
297
- "single_word": false,
298
- "lstrip": false,
299
- "rstrip": false,
300
- "normalized": true,
301
- "special": false
302
- },
303
- {
304
- "id": 34,
305
- "content": "26",
306
- "single_word": false,
307
- "lstrip": false,
308
- "rstrip": false,
309
- "normalized": true,
310
- "special": false
311
- },
312
- {
313
- "id": 35,
314
- "content": "27",
315
- "single_word": false,
316
- "lstrip": false,
317
- "rstrip": false,
318
- "normalized": true,
319
- "special": false
320
- },
321
- {
322
- "id": 36,
323
- "content": "28",
324
- "single_word": false,
325
- "lstrip": false,
326
- "rstrip": false,
327
- "normalized": true,
328
- "special": false
329
- },
330
- {
331
- "id": 37,
332
- "content": "29",
333
- "single_word": false,
334
- "lstrip": false,
335
- "rstrip": false,
336
- "normalized": true,
337
- "special": false
338
- },
339
- {
340
- "id": 38,
341
- "content": "30",
342
- "single_word": false,
343
- "lstrip": false,
344
- "rstrip": false,
345
- "normalized": true,
346
- "special": false
347
- },
348
- {
349
- "id": 39,
350
- "content": "31",
351
- "single_word": false,
352
- "lstrip": false,
353
- "rstrip": false,
354
- "normalized": true,
355
- "special": false
356
- },
357
- {
358
- "id": 40,
359
- "content": "32",
360
- "single_word": false,
361
- "lstrip": false,
362
- "rstrip": false,
363
- "normalized": true,
364
- "special": false
365
- },
366
- {
367
- "id": 41,
368
- "content": "33",
369
- "single_word": false,
370
- "lstrip": false,
371
- "rstrip": false,
372
- "normalized": true,
373
- "special": false
374
- },
375
- {
376
- "id": 42,
377
- "content": "34",
378
- "single_word": false,
379
- "lstrip": false,
380
- "rstrip": false,
381
- "normalized": true,
382
- "special": false
383
- },
384
- {
385
- "id": 43,
386
- "content": "35",
387
- "single_word": false,
388
- "lstrip": false,
389
- "rstrip": false,
390
- "normalized": true,
391
- "special": false
392
- },
393
- {
394
- "id": 44,
395
- "content": "36",
396
- "single_word": false,
397
- "lstrip": false,
398
- "rstrip": false,
399
- "normalized": true,
400
- "special": false
401
- },
402
- {
403
- "id": 45,
404
- "content": "37",
405
- "single_word": false,
406
- "lstrip": false,
407
- "rstrip": false,
408
- "normalized": true,
409
- "special": false
410
- },
411
- {
412
- "id": 46,
413
- "content": "38",
414
- "single_word": false,
415
- "lstrip": false,
416
- "rstrip": false,
417
- "normalized": true,
418
- "special": false
419
- },
420
- {
421
- "id": 47,
422
- "content": "39",
423
- "single_word": false,
424
- "lstrip": false,
425
- "rstrip": false,
426
- "normalized": true,
427
- "special": false
428
- },
429
- {
430
- "id": 48,
431
- "content": "40",
432
- "single_word": false,
433
- "lstrip": false,
434
- "rstrip": false,
435
- "normalized": true,
436
- "special": false
437
- },
438
- {
439
- "id": 49,
440
- "content": "41",
441
- "single_word": false,
442
- "lstrip": false,
443
- "rstrip": false,
444
- "normalized": true,
445
- "special": false
446
- },
447
- {
448
- "id": 50,
449
- "content": "42",
450
- "single_word": false,
451
- "lstrip": false,
452
- "rstrip": false,
453
- "normalized": true,
454
- "special": false
455
- },
456
- {
457
- "id": 51,
458
- "content": "43",
459
- "single_word": false,
460
- "lstrip": false,
461
- "rstrip": false,
462
- "normalized": true,
463
- "special": false
464
- },
465
- {
466
- "id": 52,
467
- "content": "44",
468
- "single_word": false,
469
- "lstrip": false,
470
- "rstrip": false,
471
- "normalized": true,
472
- "special": false
473
- },
474
- {
475
- "id": 53,
476
- "content": "45",
477
- "single_word": false,
478
- "lstrip": false,
479
- "rstrip": false,
480
- "normalized": true,
481
- "special": false
482
- },
483
- {
484
- "id": 54,
485
- "content": "46",
486
- "single_word": false,
487
- "lstrip": false,
488
- "rstrip": false,
489
- "normalized": true,
490
- "special": false
491
- },
492
- {
493
- "id": 55,
494
- "content": "47",
495
- "single_word": false,
496
- "lstrip": false,
497
- "rstrip": false,
498
- "normalized": true,
499
- "special": false
500
- },
501
- {
502
- "id": 56,
503
- "content": "48",
504
- "single_word": false,
505
- "lstrip": false,
506
- "rstrip": false,
507
- "normalized": true,
508
- "special": false
509
- },
510
- {
511
- "id": 57,
512
- "content": "49",
513
- "single_word": false,
514
- "lstrip": false,
515
- "rstrip": false,
516
- "normalized": true,
517
- "special": false
518
- },
519
- {
520
- "id": 58,
521
- "content": "50",
522
- "single_word": false,
523
- "lstrip": false,
524
- "rstrip": false,
525
- "normalized": true,
526
- "special": false
527
- },
528
- {
529
- "id": 59,
530
- "content": "51",
531
- "single_word": false,
532
- "lstrip": false,
533
- "rstrip": false,
534
- "normalized": true,
535
- "special": false
536
- },
537
- {
538
- "id": 60,
539
- "content": "52",
540
- "single_word": false,
541
- "lstrip": false,
542
- "rstrip": false,
543
- "normalized": true,
544
- "special": false
545
- },
546
- {
547
- "id": 61,
548
- "content": "53",
549
- "single_word": false,
550
- "lstrip": false,
551
- "rstrip": false,
552
- "normalized": true,
553
- "special": false
554
- },
555
- {
556
- "id": 62,
557
- "content": "54",
558
- "single_word": false,
559
- "lstrip": false,
560
- "rstrip": false,
561
- "normalized": true,
562
- "special": false
563
- },
564
- {
565
- "id": 63,
566
- "content": "55",
567
- "single_word": false,
568
- "lstrip": false,
569
- "rstrip": false,
570
- "normalized": true,
571
- "special": false
572
- },
573
- {
574
- "id": 64,
575
- "content": "56",
576
- "single_word": false,
577
- "lstrip": false,
578
- "rstrip": false,
579
- "normalized": true,
580
- "special": false
581
- },
582
- {
583
- "id": 65,
584
- "content": "57",
585
- "single_word": false,
586
- "lstrip": false,
587
- "rstrip": false,
588
- "normalized": true,
589
- "special": false
590
- },
591
- {
592
- "id": 66,
593
- "content": "58",
594
- "single_word": false,
595
- "lstrip": false,
596
- "rstrip": false,
597
- "normalized": true,
598
- "special": false
599
- },
600
- {
601
- "id": 67,
602
- "content": "59",
603
- "single_word": false,
604
- "lstrip": false,
605
- "rstrip": false,
606
- "normalized": true,
607
- "special": false
608
- },
609
- {
610
- "id": 68,
611
- "content": "60",
612
- "single_word": false,
613
- "lstrip": false,
614
- "rstrip": false,
615
- "normalized": true,
616
- "special": false
617
- },
618
- {
619
- "id": 69,
620
- "content": "61",
621
- "single_word": false,
622
- "lstrip": false,
623
- "rstrip": false,
624
- "normalized": true,
625
- "special": false
626
- },
627
- {
628
- "id": 70,
629
- "content": "62",
630
- "single_word": false,
631
- "lstrip": false,
632
- "rstrip": false,
633
- "normalized": true,
634
- "special": false
635
- },
636
- {
637
- "id": 71,
638
- "content": "63",
639
- "single_word": false,
640
- "lstrip": false,
641
- "rstrip": false,
642
- "normalized": true,
643
- "special": false
644
- },
645
- {
646
- "id": 72,
647
- "content": "64",
648
- "single_word": false,
649
- "lstrip": false,
650
- "rstrip": false,
651
- "normalized": true,
652
- "special": false
653
- },
654
- {
655
- "id": 73,
656
- "content": "65",
657
- "single_word": false,
658
- "lstrip": false,
659
- "rstrip": false,
660
- "normalized": true,
661
- "special": false
662
- },
663
- {
664
- "id": 74,
665
- "content": "66",
666
- "single_word": false,
667
- "lstrip": false,
668
- "rstrip": false,
669
- "normalized": true,
670
- "special": false
671
- },
672
- {
673
- "id": 75,
674
- "content": "67",
675
- "single_word": false,
676
- "lstrip": false,
677
- "rstrip": false,
678
- "normalized": true,
679
- "special": false
680
- },
681
- {
682
- "id": 76,
683
- "content": "68",
684
- "single_word": false,
685
- "lstrip": false,
686
- "rstrip": false,
687
- "normalized": true,
688
- "special": false
689
- },
690
- {
691
- "id": 77,
692
- "content": "69",
693
- "single_word": false,
694
- "lstrip": false,
695
- "rstrip": false,
696
- "normalized": true,
697
- "special": false
698
- },
699
- {
700
- "id": 78,
701
- "content": "70",
702
- "single_word": false,
703
- "lstrip": false,
704
- "rstrip": false,
705
- "normalized": true,
706
- "special": false
707
- },
708
- {
709
- "id": 79,
710
- "content": "71",
711
- "single_word": false,
712
- "lstrip": false,
713
- "rstrip": false,
714
- "normalized": true,
715
- "special": false
716
- },
717
- {
718
- "id": 80,
719
- "content": "72",
720
- "single_word": false,
721
- "lstrip": false,
722
- "rstrip": false,
723
- "normalized": true,
724
- "special": false
725
- },
726
- {
727
- "id": 81,
728
- "content": "73",
729
- "single_word": false,
730
- "lstrip": false,
731
- "rstrip": false,
732
- "normalized": true,
733
- "special": false
734
- },
735
- {
736
- "id": 82,
737
- "content": "74",
738
- "single_word": false,
739
- "lstrip": false,
740
- "rstrip": false,
741
- "normalized": true,
742
- "special": false
743
- },
744
- {
745
- "id": 83,
746
- "content": "75",
747
- "single_word": false,
748
- "lstrip": false,
749
- "rstrip": false,
750
- "normalized": true,
751
- "special": false
752
- },
753
- {
754
- "id": 84,
755
- "content": "76",
756
- "single_word": false,
757
- "lstrip": false,
758
- "rstrip": false,
759
- "normalized": true,
760
- "special": false
761
- },
762
- {
763
- "id": 85,
764
- "content": "77",
765
- "single_word": false,
766
- "lstrip": false,
767
- "rstrip": false,
768
- "normalized": true,
769
- "special": false
770
- },
771
- {
772
- "id": 86,
773
- "content": "78",
774
- "single_word": false,
775
- "lstrip": false,
776
- "rstrip": false,
777
- "normalized": true,
778
- "special": false
779
- },
780
- {
781
- "id": 87,
782
- "content": "79",
783
- "single_word": false,
784
- "lstrip": false,
785
- "rstrip": false,
786
- "normalized": true,
787
- "special": false
788
- },
789
- {
790
- "id": 88,
791
- "content": "80",
792
- "single_word": false,
793
- "lstrip": false,
794
- "rstrip": false,
795
- "normalized": true,
796
- "special": false
797
- },
798
- {
799
- "id": 89,
800
- "content": "81",
801
- "single_word": false,
802
- "lstrip": false,
803
- "rstrip": false,
804
- "normalized": true,
805
- "special": false
806
- },
807
- {
808
- "id": 90,
809
- "content": "82",
810
- "single_word": false,
811
- "lstrip": false,
812
- "rstrip": false,
813
- "normalized": true,
814
- "special": false
815
- },
816
- {
817
- "id": 91,
818
- "content": "83",
819
- "single_word": false,
820
- "lstrip": false,
821
- "rstrip": false,
822
- "normalized": true,
823
- "special": false
824
- },
825
- {
826
- "id": 92,
827
- "content": "84",
828
- "single_word": false,
829
- "lstrip": false,
830
- "rstrip": false,
831
- "normalized": true,
832
- "special": false
833
- },
834
- {
835
- "id": 93,
836
- "content": "85",
837
- "single_word": false,
838
- "lstrip": false,
839
- "rstrip": false,
840
- "normalized": true,
841
- "special": false
842
- },
843
- {
844
- "id": 94,
845
- "content": "86",
846
- "single_word": false,
847
- "lstrip": false,
848
- "rstrip": false,
849
- "normalized": true,
850
- "special": false
851
- },
852
- {
853
- "id": 95,
854
- "content": "87",
855
- "single_word": false,
856
- "lstrip": false,
857
- "rstrip": false,
858
- "normalized": true,
859
- "special": false
860
- },
861
- {
862
- "id": 96,
863
- "content": "88",
864
- "single_word": false,
865
- "lstrip": false,
866
- "rstrip": false,
867
- "normalized": true,
868
- "special": false
869
- },
870
- {
871
- "id": 97,
872
- "content": "89",
873
- "single_word": false,
874
- "lstrip": false,
875
- "rstrip": false,
876
- "normalized": true,
877
- "special": false
878
- },
879
- {
880
- "id": 98,
881
- "content": "90",
882
- "single_word": false,
883
- "lstrip": false,
884
- "rstrip": false,
885
- "normalized": true,
886
- "special": false
887
- },
888
- {
889
- "id": 99,
890
- "content": "91",
891
- "single_word": false,
892
- "lstrip": false,
893
- "rstrip": false,
894
- "normalized": true,
895
- "special": false
896
- },
897
- {
898
- "id": 100,
899
- "content": "92",
900
- "single_word": false,
901
- "lstrip": false,
902
- "rstrip": false,
903
- "normalized": true,
904
- "special": false
905
- },
906
- {
907
- "id": 101,
908
- "content": "93",
909
- "single_word": false,
910
- "lstrip": false,
911
- "rstrip": false,
912
- "normalized": true,
913
- "special": false
914
- },
915
- {
916
- "id": 102,
917
- "content": "94",
918
- "single_word": false,
919
- "lstrip": false,
920
- "rstrip": false,
921
- "normalized": true,
922
- "special": false
923
- },
924
- {
925
- "id": 103,
926
- "content": "95",
927
- "single_word": false,
928
- "lstrip": false,
929
- "rstrip": false,
930
- "normalized": true,
931
- "special": false
932
- },
933
- {
934
- "id": 104,
935
- "content": "96",
936
- "single_word": false,
937
- "lstrip": false,
938
- "rstrip": false,
939
- "normalized": true,
940
- "special": false
941
- },
942
- {
943
- "id": 105,
944
- "content": "97",
945
- "single_word": false,
946
- "lstrip": false,
947
- "rstrip": false,
948
- "normalized": true,
949
- "special": false
950
- },
951
- {
952
- "id": 106,
953
- "content": "98",
954
- "single_word": false,
955
- "lstrip": false,
956
- "rstrip": false,
957
- "normalized": true,
958
- "special": false
959
- },
960
- {
961
- "id": 107,
962
- "content": " 0",
963
- "single_word": false,
964
- "lstrip": false,
965
- "rstrip": false,
966
- "normalized": true,
967
- "special": false
968
- },
969
- {
970
- "id": 108,
971
- "content": " 1",
972
- "single_word": false,
973
- "lstrip": false,
974
- "rstrip": false,
975
- "normalized": true,
976
- "special": false
977
- },
978
- {
979
- "id": 109,
980
- "content": " 2",
981
- "single_word": false,
982
- "lstrip": false,
983
- "rstrip": false,
984
- "normalized": true,
985
- "special": false
986
- },
987
- {
988
- "id": 110,
989
- "content": " 3",
990
- "single_word": false,
991
- "lstrip": false,
992
- "rstrip": false,
993
- "normalized": true,
994
- "special": false
995
- },
996
- {
997
- "id": 111,
998
- "content": " 4",
999
- "single_word": false,
1000
- "lstrip": false,
1001
- "rstrip": false,
1002
- "normalized": true,
1003
- "special": false
1004
- },
1005
- {
1006
- "id": 112,
1007
- "content": " 5",
1008
- "single_word": false,
1009
- "lstrip": false,
1010
- "rstrip": false,
1011
- "normalized": true,
1012
- "special": false
1013
- },
1014
- {
1015
- "id": 113,
1016
- "content": " 6",
1017
- "single_word": false,
1018
- "lstrip": false,
1019
- "rstrip": false,
1020
- "normalized": true,
1021
- "special": false
1022
- },
1023
- {
1024
- "id": 114,
1025
- "content": " 7",
1026
- "single_word": false,
1027
- "lstrip": false,
1028
- "rstrip": false,
1029
- "normalized": true,
1030
- "special": false
1031
- },
1032
- {
1033
- "id": 115,
1034
- "content": " 8",
1035
- "single_word": false,
1036
- "lstrip": false,
1037
- "rstrip": false,
1038
- "normalized": true,
1039
- "special": false
1040
- },
1041
- {
1042
- "id": 116,
1043
- "content": " 9",
1044
- "single_word": false,
1045
- "lstrip": false,
1046
- "rstrip": false,
1047
- "normalized": true,
1048
- "special": false
1049
- },
1050
- {
1051
- "id": 117,
1052
- "content": "99",
1053
- "single_word": false,
1054
- "lstrip": false,
1055
- "rstrip": false,
1056
- "normalized": true,
1057
- "special": false
1058
  }
1059
  ],
1060
  "normalizer": null,
@@ -1111,96 +121,96 @@
1111
  "7": 14,
1112
  "8": 15,
1113
  "9": 16,
1114
- "Ġ": 17,
1115
- "10": 18,
1116
- "11": 19,
1117
- "12": 20,
1118
- "13": 21,
1119
- "14": 22,
1120
- "15": 23,
1121
- "16": 24,
1122
- "17": 25,
1123
- "18": 26,
1124
- "19": 27,
1125
- "20": 28,
1126
- "21": 29,
1127
- "22": 30,
1128
- "23": 31,
1129
- "24": 32,
1130
- "25": 33,
1131
- "26": 34,
1132
- "27": 35,
1133
- "28": 36,
1134
- "29": 37,
1135
- "30": 38,
1136
- "31": 39,
1137
- "32": 40,
1138
- "33": 41,
1139
- "34": 42,
1140
- "35": 43,
1141
- "36": 44,
1142
- "37": 45,
1143
- "38": 46,
1144
- "39": 47,
1145
- "40": 48,
1146
- "41": 49,
1147
- "42": 50,
1148
- "43": 51,
1149
- "44": 52,
1150
- "45": 53,
1151
- "46": 54,
1152
- "47": 55,
1153
- "48": 56,
1154
- "49": 57,
1155
- "50": 58,
1156
- "51": 59,
1157
- "52": 60,
1158
- "53": 61,
1159
- "54": 62,
1160
- "55": 63,
1161
- "56": 64,
1162
- "57": 65,
1163
- "58": 66,
1164
- "59": 67,
1165
- "60": 68,
1166
- "61": 69,
1167
- "62": 70,
1168
- "63": 71,
1169
- "64": 72,
1170
- "65": 73,
1171
- "66": 74,
1172
- "67": 75,
1173
- "68": 76,
1174
- "69": 77,
1175
- "70": 78,
1176
- "71": 79,
1177
- "72": 80,
1178
- "73": 81,
1179
- "74": 82,
1180
- "75": 83,
1181
- "76": 84,
1182
- "77": 85,
1183
- "78": 86,
1184
- "79": 87,
1185
- "80": 88,
1186
- "81": 89,
1187
- "82": 90,
1188
- "83": 91,
1189
- "84": 92,
1190
- "85": 93,
1191
- "86": 94,
1192
- "87": 95,
1193
- "88": 96,
1194
- "89": 97,
1195
- "90": 98,
1196
- "91": 99,
1197
- "92": 100,
1198
- "93": 101,
1199
- "94": 102,
1200
- "95": 103,
1201
- "96": 104,
1202
- "97": 105,
1203
- "98": 106
1204
  },
1205
  "merges": [
1206
  [
@@ -1558,6 +568,10 @@
1558
  [
1559
  "9",
1560
  "8"
 
 
 
 
1561
  ]
1562
  ]
1563
  }
 
65
  "rstrip": false,
66
  "normalized": false,
67
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "normalizer": null,
 
121
  "7": 14,
122
  "8": 15,
123
  "9": 16,
124
+ "10": 17,
125
+ "11": 18,
126
+ "12": 19,
127
+ "13": 20,
128
+ "14": 21,
129
+ "15": 22,
130
+ "16": 23,
131
+ "17": 24,
132
+ "18": 25,
133
+ "19": 26,
134
+ "20": 27,
135
+ "21": 28,
136
+ "22": 29,
137
+ "23": 30,
138
+ "24": 31,
139
+ "25": 32,
140
+ "26": 33,
141
+ "27": 34,
142
+ "28": 35,
143
+ "29": 36,
144
+ "30": 37,
145
+ "31": 38,
146
+ "32": 39,
147
+ "33": 40,
148
+ "34": 41,
149
+ "35": 42,
150
+ "36": 43,
151
+ "37": 44,
152
+ "38": 45,
153
+ "39": 46,
154
+ "40": 47,
155
+ "41": 48,
156
+ "42": 49,
157
+ "43": 50,
158
+ "44": 51,
159
+ "45": 52,
160
+ "46": 53,
161
+ "47": 54,
162
+ "48": 55,
163
+ "49": 56,
164
+ "50": 57,
165
+ "51": 58,
166
+ "52": 59,
167
+ "53": 60,
168
+ "54": 61,
169
+ "55": 62,
170
+ "56": 63,
171
+ "57": 64,
172
+ "58": 65,
173
+ "59": 66,
174
+ "60": 67,
175
+ "61": 68,
176
+ "62": 69,
177
+ "63": 70,
178
+ "64": 71,
179
+ "65": 72,
180
+ "66": 73,
181
+ "67": 74,
182
+ "68": 75,
183
+ "69": 76,
184
+ "70": 77,
185
+ "71": 78,
186
+ "72": 79,
187
+ "73": 80,
188
+ "74": 81,
189
+ "75": 82,
190
+ "76": 83,
191
+ "77": 84,
192
+ "78": 85,
193
+ "79": 86,
194
+ "80": 87,
195
+ "81": 88,
196
+ "82": 89,
197
+ "83": 90,
198
+ "84": 91,
199
+ "85": 92,
200
+ "86": 93,
201
+ "87": 94,
202
+ "88": 95,
203
+ "89": 96,
204
+ "90": 97,
205
+ "91": 98,
206
+ "92": 99,
207
+ "93": 100,
208
+ "94": 101,
209
+ "95": 102,
210
+ "96": 103,
211
+ "97": 104,
212
+ "98": 105,
213
+ "99": 106
214
  },
215
  "merges": [
216
  [
 
568
  [
569
  "9",
570
  "8"
571
+ ],
572
+ [
573
+ "9",
574
+ "9"
575
  ]
576
  ]
577
  }
tokenizer_config.json CHANGED
@@ -55,886 +55,6 @@
55
  "rstrip": false,
56
  "single_word": false,
57
  "special": true
58
- },
59
- "7": {
60
- "content": "0",
61
- "lstrip": false,
62
- "normalized": true,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": false
66
- },
67
- "8": {
68
- "content": "1",
69
- "lstrip": false,
70
- "normalized": true,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": false
74
- },
75
- "9": {
76
- "content": "2",
77
- "lstrip": false,
78
- "normalized": true,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": false
82
- },
83
- "10": {
84
- "content": "3",
85
- "lstrip": false,
86
- "normalized": true,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": false
90
- },
91
- "11": {
92
- "content": "4",
93
- "lstrip": false,
94
- "normalized": true,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": false
98
- },
99
- "12": {
100
- "content": "5",
101
- "lstrip": false,
102
- "normalized": true,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": false
106
- },
107
- "13": {
108
- "content": "6",
109
- "lstrip": false,
110
- "normalized": true,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": false
114
- },
115
- "14": {
116
- "content": "7",
117
- "lstrip": false,
118
- "normalized": true,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": false
122
- },
123
- "15": {
124
- "content": "8",
125
- "lstrip": false,
126
- "normalized": true,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": false
130
- },
131
- "16": {
132
- "content": "9",
133
- "lstrip": false,
134
- "normalized": true,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": false
138
- },
139
- "18": {
140
- "content": "10",
141
- "lstrip": false,
142
- "normalized": true,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": false
146
- },
147
- "19": {
148
- "content": "11",
149
- "lstrip": false,
150
- "normalized": true,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": false
154
- },
155
- "20": {
156
- "content": "12",
157
- "lstrip": false,
158
- "normalized": true,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": false
162
- },
163
- "21": {
164
- "content": "13",
165
- "lstrip": false,
166
- "normalized": true,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": false
170
- },
171
- "22": {
172
- "content": "14",
173
- "lstrip": false,
174
- "normalized": true,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": false
178
- },
179
- "23": {
180
- "content": "15",
181
- "lstrip": false,
182
- "normalized": true,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": false
186
- },
187
- "24": {
188
- "content": "16",
189
- "lstrip": false,
190
- "normalized": true,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": false
194
- },
195
- "25": {
196
- "content": "17",
197
- "lstrip": false,
198
- "normalized": true,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": false
202
- },
203
- "26": {
204
- "content": "18",
205
- "lstrip": false,
206
- "normalized": true,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": false
210
- },
211
- "27": {
212
- "content": "19",
213
- "lstrip": false,
214
- "normalized": true,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": false
218
- },
219
- "28": {
220
- "content": "20",
221
- "lstrip": false,
222
- "normalized": true,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": false
226
- },
227
- "29": {
228
- "content": "21",
229
- "lstrip": false,
230
- "normalized": true,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": false
234
- },
235
- "30": {
236
- "content": "22",
237
- "lstrip": false,
238
- "normalized": true,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": false
242
- },
243
- "31": {
244
- "content": "23",
245
- "lstrip": false,
246
- "normalized": true,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": false
250
- },
251
- "32": {
252
- "content": "24",
253
- "lstrip": false,
254
- "normalized": true,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": false
258
- },
259
- "33": {
260
- "content": "25",
261
- "lstrip": false,
262
- "normalized": true,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": false
266
- },
267
- "34": {
268
- "content": "26",
269
- "lstrip": false,
270
- "normalized": true,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": false
274
- },
275
- "35": {
276
- "content": "27",
277
- "lstrip": false,
278
- "normalized": true,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": false
282
- },
283
- "36": {
284
- "content": "28",
285
- "lstrip": false,
286
- "normalized": true,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": false
290
- },
291
- "37": {
292
- "content": "29",
293
- "lstrip": false,
294
- "normalized": true,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": false
298
- },
299
- "38": {
300
- "content": "30",
301
- "lstrip": false,
302
- "normalized": true,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": false
306
- },
307
- "39": {
308
- "content": "31",
309
- "lstrip": false,
310
- "normalized": true,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": false
314
- },
315
- "40": {
316
- "content": "32",
317
- "lstrip": false,
318
- "normalized": true,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": false
322
- },
323
- "41": {
324
- "content": "33",
325
- "lstrip": false,
326
- "normalized": true,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": false
330
- },
331
- "42": {
332
- "content": "34",
333
- "lstrip": false,
334
- "normalized": true,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": false
338
- },
339
- "43": {
340
- "content": "35",
341
- "lstrip": false,
342
- "normalized": true,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": false
346
- },
347
- "44": {
348
- "content": "36",
349
- "lstrip": false,
350
- "normalized": true,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": false
354
- },
355
- "45": {
356
- "content": "37",
357
- "lstrip": false,
358
- "normalized": true,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": false
362
- },
363
- "46": {
364
- "content": "38",
365
- "lstrip": false,
366
- "normalized": true,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": false
370
- },
371
- "47": {
372
- "content": "39",
373
- "lstrip": false,
374
- "normalized": true,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": false
378
- },
379
- "48": {
380
- "content": "40",
381
- "lstrip": false,
382
- "normalized": true,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": false
386
- },
387
- "49": {
388
- "content": "41",
389
- "lstrip": false,
390
- "normalized": true,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": false
394
- },
395
- "50": {
396
- "content": "42",
397
- "lstrip": false,
398
- "normalized": true,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": false
402
- },
403
- "51": {
404
- "content": "43",
405
- "lstrip": false,
406
- "normalized": true,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": false
410
- },
411
- "52": {
412
- "content": "44",
413
- "lstrip": false,
414
- "normalized": true,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": false
418
- },
419
- "53": {
420
- "content": "45",
421
- "lstrip": false,
422
- "normalized": true,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": false
426
- },
427
- "54": {
428
- "content": "46",
429
- "lstrip": false,
430
- "normalized": true,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": false
434
- },
435
- "55": {
436
- "content": "47",
437
- "lstrip": false,
438
- "normalized": true,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": false
442
- },
443
- "56": {
444
- "content": "48",
445
- "lstrip": false,
446
- "normalized": true,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": false
450
- },
451
- "57": {
452
- "content": "49",
453
- "lstrip": false,
454
- "normalized": true,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": false
458
- },
459
- "58": {
460
- "content": "50",
461
- "lstrip": false,
462
- "normalized": true,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": false
466
- },
467
- "59": {
468
- "content": "51",
469
- "lstrip": false,
470
- "normalized": true,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": false
474
- },
475
- "60": {
476
- "content": "52",
477
- "lstrip": false,
478
- "normalized": true,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": false
482
- },
483
- "61": {
484
- "content": "53",
485
- "lstrip": false,
486
- "normalized": true,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": false
490
- },
491
- "62": {
492
- "content": "54",
493
- "lstrip": false,
494
- "normalized": true,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": false
498
- },
499
- "63": {
500
- "content": "55",
501
- "lstrip": false,
502
- "normalized": true,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": false
506
- },
507
- "64": {
508
- "content": "56",
509
- "lstrip": false,
510
- "normalized": true,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": false
514
- },
515
- "65": {
516
- "content": "57",
517
- "lstrip": false,
518
- "normalized": true,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": false
522
- },
523
- "66": {
524
- "content": "58",
525
- "lstrip": false,
526
- "normalized": true,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": false
530
- },
531
- "67": {
532
- "content": "59",
533
- "lstrip": false,
534
- "normalized": true,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": false
538
- },
539
- "68": {
540
- "content": "60",
541
- "lstrip": false,
542
- "normalized": true,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": false
546
- },
547
- "69": {
548
- "content": "61",
549
- "lstrip": false,
550
- "normalized": true,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": false
554
- },
555
- "70": {
556
- "content": "62",
557
- "lstrip": false,
558
- "normalized": true,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": false
562
- },
563
- "71": {
564
- "content": "63",
565
- "lstrip": false,
566
- "normalized": true,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": false
570
- },
571
- "72": {
572
- "content": "64",
573
- "lstrip": false,
574
- "normalized": true,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": false
578
- },
579
- "73": {
580
- "content": "65",
581
- "lstrip": false,
582
- "normalized": true,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": false
586
- },
587
- "74": {
588
- "content": "66",
589
- "lstrip": false,
590
- "normalized": true,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": false
594
- },
595
- "75": {
596
- "content": "67",
597
- "lstrip": false,
598
- "normalized": true,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": false
602
- },
603
- "76": {
604
- "content": "68",
605
- "lstrip": false,
606
- "normalized": true,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": false
610
- },
611
- "77": {
612
- "content": "69",
613
- "lstrip": false,
614
- "normalized": true,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": false
618
- },
619
- "78": {
620
- "content": "70",
621
- "lstrip": false,
622
- "normalized": true,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": false
626
- },
627
- "79": {
628
- "content": "71",
629
- "lstrip": false,
630
- "normalized": true,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": false
634
- },
635
- "80": {
636
- "content": "72",
637
- "lstrip": false,
638
- "normalized": true,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": false
642
- },
643
- "81": {
644
- "content": "73",
645
- "lstrip": false,
646
- "normalized": true,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": false
650
- },
651
- "82": {
652
- "content": "74",
653
- "lstrip": false,
654
- "normalized": true,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": false
658
- },
659
- "83": {
660
- "content": "75",
661
- "lstrip": false,
662
- "normalized": true,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": false
666
- },
667
- "84": {
668
- "content": "76",
669
- "lstrip": false,
670
- "normalized": true,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": false
674
- },
675
- "85": {
676
- "content": "77",
677
- "lstrip": false,
678
- "normalized": true,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": false
682
- },
683
- "86": {
684
- "content": "78",
685
- "lstrip": false,
686
- "normalized": true,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": false
690
- },
691
- "87": {
692
- "content": "79",
693
- "lstrip": false,
694
- "normalized": true,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": false
698
- },
699
- "88": {
700
- "content": "80",
701
- "lstrip": false,
702
- "normalized": true,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": false
706
- },
707
- "89": {
708
- "content": "81",
709
- "lstrip": false,
710
- "normalized": true,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": false
714
- },
715
- "90": {
716
- "content": "82",
717
- "lstrip": false,
718
- "normalized": true,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": false
722
- },
723
- "91": {
724
- "content": "83",
725
- "lstrip": false,
726
- "normalized": true,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": false
730
- },
731
- "92": {
732
- "content": "84",
733
- "lstrip": false,
734
- "normalized": true,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": false
738
- },
739
- "93": {
740
- "content": "85",
741
- "lstrip": false,
742
- "normalized": true,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": false
746
- },
747
- "94": {
748
- "content": "86",
749
- "lstrip": false,
750
- "normalized": true,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": false
754
- },
755
- "95": {
756
- "content": "87",
757
- "lstrip": false,
758
- "normalized": true,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": false
762
- },
763
- "96": {
764
- "content": "88",
765
- "lstrip": false,
766
- "normalized": true,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": false
770
- },
771
- "97": {
772
- "content": "89",
773
- "lstrip": false,
774
- "normalized": true,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": false
778
- },
779
- "98": {
780
- "content": "90",
781
- "lstrip": false,
782
- "normalized": true,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": false
786
- },
787
- "99": {
788
- "content": "91",
789
- "lstrip": false,
790
- "normalized": true,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": false
794
- },
795
- "100": {
796
- "content": "92",
797
- "lstrip": false,
798
- "normalized": true,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": false
802
- },
803
- "101": {
804
- "content": "93",
805
- "lstrip": false,
806
- "normalized": true,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": false
810
- },
811
- "102": {
812
- "content": "94",
813
- "lstrip": false,
814
- "normalized": true,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": false
818
- },
819
- "103": {
820
- "content": "95",
821
- "lstrip": false,
822
- "normalized": true,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": false
826
- },
827
- "104": {
828
- "content": "96",
829
- "lstrip": false,
830
- "normalized": true,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": false
834
- },
835
- "105": {
836
- "content": "97",
837
- "lstrip": false,
838
- "normalized": true,
839
- "rstrip": false,
840
- "single_word": false,
841
- "special": false
842
- },
843
- "106": {
844
- "content": "98",
845
- "lstrip": false,
846
- "normalized": true,
847
- "rstrip": false,
848
- "single_word": false,
849
- "special": false
850
- },
851
- "107": {
852
- "content": " 0",
853
- "lstrip": false,
854
- "normalized": true,
855
- "rstrip": false,
856
- "single_word": false,
857
- "special": false
858
- },
859
- "108": {
860
- "content": " 1",
861
- "lstrip": false,
862
- "normalized": true,
863
- "rstrip": false,
864
- "single_word": false,
865
- "special": false
866
- },
867
- "109": {
868
- "content": " 2",
869
- "lstrip": false,
870
- "normalized": true,
871
- "rstrip": false,
872
- "single_word": false,
873
- "special": false
874
- },
875
- "110": {
876
- "content": " 3",
877
- "lstrip": false,
878
- "normalized": true,
879
- "rstrip": false,
880
- "single_word": false,
881
- "special": false
882
- },
883
- "111": {
884
- "content": " 4",
885
- "lstrip": false,
886
- "normalized": true,
887
- "rstrip": false,
888
- "single_word": false,
889
- "special": false
890
- },
891
- "112": {
892
- "content": " 5",
893
- "lstrip": false,
894
- "normalized": true,
895
- "rstrip": false,
896
- "single_word": false,
897
- "special": false
898
- },
899
- "113": {
900
- "content": " 6",
901
- "lstrip": false,
902
- "normalized": true,
903
- "rstrip": false,
904
- "single_word": false,
905
- "special": false
906
- },
907
- "114": {
908
- "content": " 7",
909
- "lstrip": false,
910
- "normalized": true,
911
- "rstrip": false,
912
- "single_word": false,
913
- "special": false
914
- },
915
- "115": {
916
- "content": " 8",
917
- "lstrip": false,
918
- "normalized": true,
919
- "rstrip": false,
920
- "single_word": false,
921
- "special": false
922
- },
923
- "116": {
924
- "content": " 9",
925
- "lstrip": false,
926
- "normalized": true,
927
- "rstrip": false,
928
- "single_word": false,
929
- "special": false
930
- },
931
- "117": {
932
- "content": "99",
933
- "lstrip": false,
934
- "normalized": true,
935
- "rstrip": false,
936
- "single_word": false,
937
- "special": false
938
  }
939
  },
940
  "additional_special_tokens": [
 
55
  "rstrip": false,
56
  "single_word": false,
57
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  }
59
  },
60
  "additional_special_tokens": [
vocab.json CHANGED
@@ -1,109 +1,109 @@
1
  {
2
- "40": 48,
3
- "37": 45,
4
- "53": 61,
 
 
 
 
 
 
 
 
 
 
5
  "5": 12,
6
- "29": 37,
7
- "91": 99,
8
- "68": 76,
9
- "55": 63,
10
- "75": 83,
11
- "97": 105,
12
- "4": 11,
13
- "47": 55,
14
  "3": 10,
 
 
 
 
 
 
 
 
 
 
 
15
  "<s>": 1,
16
- "87": 95,
17
- "88": 96,
 
 
 
 
 
 
 
 
 
 
 
 
18
  "7": 14,
19
- "20": 28,
20
- "Ġ": 17,
21
- "45": 53,
22
- "57": 65,
23
- "49": 57,
24
- "76": 84,
25
- "19": 27,
26
- "69": 77,
27
- "23": 31,
28
- "41": 49,
29
- "8": 15,
30
- "89": 97,
31
- "17": 25,
32
- "66": 74,
33
- "65": 73,
34
- "18": 26,
35
- "84": 92,
36
- "51": 59,
37
- "67": 75,
38
- "21": 29,
39
- "56": 64,
40
- "38": 46,
41
- "44": 52,
42
- "28": 36,
43
- "26": 34,
44
- "92": 100,
45
- "72": 80,
46
- "31": 39,
47
- "90": 98,
48
- "52": 60,
49
- "39": 47,
50
- "50": 58,
51
- "81": 89,
52
- "94": 102,
53
- "13": 21,
54
- "25": 33,
55
- "9": 16,
56
- "6": 13,
57
- "80": 88,
58
- "98": 106,
59
  " ": 6,
60
- "48": 56,
61
- "33": 41,
62
- "46": 54,
63
- "71": 79,
64
- "12": 20,
65
- "96": 104,
66
- "10": 18,
67
- "59": 67,
68
- "34": 42,
69
- "74": 82,
70
- "58": 66,
71
- "27": 35,
72
- "70": 78,
73
- "73": 81,
74
- "54": 62,
75
- "=": 5,
76
- "83": 91,
77
- "mod": 4,
78
- "82": 90,
79
- "60": 68,
80
- "2": 9,
81
- "95": 103,
82
- "93": 101,
83
- "77": 85,
84
- "79": 87,
85
- "63": 71,
86
- "85": 93,
87
- "0": 7,
88
- "30": 38,
89
- "35": 43,
90
- "42": 50,
91
- "22": 30,
92
- "<unk>": 0,
93
- "64": 72,
94
  "1": 8,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95
  "<pad>": 3,
96
- "61": 69,
97
- "16": 24,
98
- "62": 70,
99
- "15": 23,
100
- "32": 40,
101
- "86": 94,
102
- "24": 32,
103
- "11": 19,
104
- "78": 86,
105
- "</s>": 2,
106
- "43": 51,
107
- "14": 22,
108
- "36": 44
 
 
 
 
 
 
 
 
 
 
 
109
  }
 
1
  {
2
+ "17": 24,
3
+ "43": 50,
4
+ "16": 23,
5
+ "57": 64,
6
+ "9": 16,
7
+ "31": 38,
8
+ "</s>": 2,
9
+ "44": 51,
10
+ "26": 33,
11
+ "56": 63,
12
+ "21": 28,
13
+ "66": 73,
14
+ "48": 55,
15
  "5": 12,
16
+ "=": 5,
 
 
 
 
 
 
 
17
  "3": 10,
18
+ "94": 101,
19
+ "46": 53,
20
+ "71": 78,
21
+ "81": 88,
22
+ "61": 68,
23
+ "42": 49,
24
+ "4": 11,
25
+ "41": 48,
26
+ "65": 72,
27
+ "62": 69,
28
+ "<unk>": 0,
29
  "<s>": 1,
30
+ "11": 18,
31
+ "0": 7,
32
+ "36": 43,
33
+ "73": 80,
34
+ "30": 37,
35
+ "40": 47,
36
+ "mod": 4,
37
+ "22": 29,
38
+ "72": 79,
39
+ "87": 94,
40
+ "88": 95,
41
+ "76": 83,
42
+ "35": 42,
43
+ "99": 106,
44
  "7": 14,
45
+ "34": 41,
46
+ "58": 65,
47
+ "23": 30,
48
+ "64": 71,
49
+ "25": 32,
50
+ "60": 67,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51
  " ": 6,
52
+ "14": 21,
53
+ "45": 52,
54
+ "32": 39,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  "1": 8,
56
+ "12": 19,
57
+ "50": 57,
58
+ "47": 54,
59
+ "67": 74,
60
+ "74": 81,
61
+ "18": 25,
62
+ "49": 56,
63
+ "85": 92,
64
+ "90": 97,
65
+ "2": 9,
66
+ "6": 13,
67
+ "15": 22,
68
+ "82": 89,
69
+ "27": 34,
70
+ "69": 76,
71
+ "79": 86,
72
+ "39": 46,
73
+ "97": 104,
74
+ "53": 60,
75
+ "8": 15,
76
+ "33": 40,
77
+ "13": 20,
78
+ "52": 59,
79
+ "96": 103,
80
+ "10": 17,
81
+ "37": 44,
82
+ "93": 100,
83
+ "89": 96,
84
  "<pad>": 3,
85
+ "80": 87,
86
+ "24": 31,
87
+ "28": 35,
88
+ "68": 75,
89
+ "38": 45,
90
+ "55": 62,
91
+ "84": 91,
92
+ "63": 70,
93
+ "19": 26,
94
+ "86": 93,
95
+ "91": 98,
96
+ "51": 58,
97
+ "20": 27,
98
+ "54": 61,
99
+ "75": 82,
100
+ "29": 36,
101
+ "77": 84,
102
+ "59": 66,
103
+ "98": 105,
104
+ "83": 90,
105
+ "95": 102,
106
+ "78": 85,
107
+ "70": 77,
108
+ "92": 99
109
  }