Safetensors
llama
phmartins commited on
Commit
43d767a
1 Parent(s): ed85302

Upload 7 files

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/mnt/cephfs-nvme/nunomg/axolotl/EuroLLM-1B/SFT-EuroBlocks-v0.1/checkpoint-1650",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -12,7 +12,6 @@
12
  "initializer_range": 0.02,
13
  "intermediate_size": 5632,
14
  "max_position_embeddings": 4096,
15
- "mlp_bias": false,
16
  "model_type": "llama",
17
  "num_attention_heads": 16,
18
  "num_hidden_layers": 24,
@@ -23,7 +22,7 @@
23
  "rope_theta": 10000.0,
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
- "transformers_version": "4.42.4",
27
  "use_cache": false,
28
  "vocab_size": 128000
29
  }
 
1
  {
2
+ "_name_or_path": "Unbabel/EuroLLM-1B-annealed",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
12
  "initializer_range": 0.02,
13
  "intermediate_size": 5632,
14
  "max_position_embeddings": 4096,
 
15
  "model_type": "llama",
16
  "num_attention_heads": 16,
17
  "num_hidden_layers": 24,
 
22
  "rope_theta": 10000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
+ "transformers_version": "4.40.0.dev0",
26
  "use_cache": false,
27
  "vocab_size": 128000
28
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 1,
4
  "do_sample": true,
5
  "eos_token_id": 2,
6
- "transformers_version": "4.42.4"
7
  }
 
3
  "bos_token_id": 1,
4
  "do_sample": true,
5
  "eos_token_id": 2,
6
+ "transformers_version": "4.40.0.dev0"
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8a05f6ae0ce4b542e30421fdddd364c734a598d5c31e1f60a2d2bf2b201fc32
3
  size 3313726248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8360c65bcc8b11723ec2cd60cfba5f960846727cd04c4d6edb0650538df6525
3
  size 3313726248
special_tokens_map.json CHANGED
@@ -13,13 +13,7 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
  "unk_token": {
24
  "content": "<unk>",
25
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "</s>",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
tokenizer.json CHANGED
@@ -47,2310 +47,6 @@
47
  "rstrip": false,
48
  "normalized": false,
49
  "special": true
50
- },
51
- {
52
- "id": 5,
53
- "content": "<extra_id_0>",
54
- "single_word": false,
55
- "lstrip": false,
56
- "rstrip": false,
57
- "normalized": false,
58
- "special": false
59
- },
60
- {
61
- "id": 6,
62
- "content": "<extra_id_1>",
63
- "single_word": false,
64
- "lstrip": false,
65
- "rstrip": false,
66
- "normalized": false,
67
- "special": false
68
- },
69
- {
70
- "id": 7,
71
- "content": "<extra_id_2>",
72
- "single_word": false,
73
- "lstrip": false,
74
- "rstrip": false,
75
- "normalized": false,
76
- "special": false
77
- },
78
- {
79
- "id": 8,
80
- "content": "<extra_id_3>",
81
- "single_word": false,
82
- "lstrip": false,
83
- "rstrip": false,
84
- "normalized": false,
85
- "special": false
86
- },
87
- {
88
- "id": 9,
89
- "content": "<extra_id_4>",
90
- "single_word": false,
91
- "lstrip": false,
92
- "rstrip": false,
93
- "normalized": false,
94
- "special": false
95
- },
96
- {
97
- "id": 10,
98
- "content": "<extra_id_5>",
99
- "single_word": false,
100
- "lstrip": false,
101
- "rstrip": false,
102
- "normalized": false,
103
- "special": false
104
- },
105
- {
106
- "id": 11,
107
- "content": "<extra_id_6>",
108
- "single_word": false,
109
- "lstrip": false,
110
- "rstrip": false,
111
- "normalized": false,
112
- "special": false
113
- },
114
- {
115
- "id": 12,
116
- "content": "<extra_id_7>",
117
- "single_word": false,
118
- "lstrip": false,
119
- "rstrip": false,
120
- "normalized": false,
121
- "special": false
122
- },
123
- {
124
- "id": 13,
125
- "content": "<extra_id_8>",
126
- "single_word": false,
127
- "lstrip": false,
128
- "rstrip": false,
129
- "normalized": false,
130
- "special": false
131
- },
132
- {
133
- "id": 14,
134
- "content": "<extra_id_9>",
135
- "single_word": false,
136
- "lstrip": false,
137
- "rstrip": false,
138
- "normalized": false,
139
- "special": false
140
- },
141
- {
142
- "id": 15,
143
- "content": "<extra_id_10>",
144
- "single_word": false,
145
- "lstrip": false,
146
- "rstrip": false,
147
- "normalized": false,
148
- "special": false
149
- },
150
- {
151
- "id": 16,
152
- "content": "<extra_id_11>",
153
- "single_word": false,
154
- "lstrip": false,
155
- "rstrip": false,
156
- "normalized": false,
157
- "special": false
158
- },
159
- {
160
- "id": 17,
161
- "content": "<extra_id_12>",
162
- "single_word": false,
163
- "lstrip": false,
164
- "rstrip": false,
165
- "normalized": false,
166
- "special": false
167
- },
168
- {
169
- "id": 18,
170
- "content": "<extra_id_13>",
171
- "single_word": false,
172
- "lstrip": false,
173
- "rstrip": false,
174
- "normalized": false,
175
- "special": false
176
- },
177
- {
178
- "id": 19,
179
- "content": "<extra_id_14>",
180
- "single_word": false,
181
- "lstrip": false,
182
- "rstrip": false,
183
- "normalized": false,
184
- "special": false
185
- },
186
- {
187
- "id": 20,
188
- "content": "<extra_id_15>",
189
- "single_word": false,
190
- "lstrip": false,
191
- "rstrip": false,
192
- "normalized": false,
193
- "special": false
194
- },
195
- {
196
- "id": 21,
197
- "content": "<extra_id_16>",
198
- "single_word": false,
199
- "lstrip": false,
200
- "rstrip": false,
201
- "normalized": false,
202
- "special": false
203
- },
204
- {
205
- "id": 22,
206
- "content": "<extra_id_17>",
207
- "single_word": false,
208
- "lstrip": false,
209
- "rstrip": false,
210
- "normalized": false,
211
- "special": false
212
- },
213
- {
214
- "id": 23,
215
- "content": "<extra_id_18>",
216
- "single_word": false,
217
- "lstrip": false,
218
- "rstrip": false,
219
- "normalized": false,
220
- "special": false
221
- },
222
- {
223
- "id": 24,
224
- "content": "<extra_id_19>",
225
- "single_word": false,
226
- "lstrip": false,
227
- "rstrip": false,
228
- "normalized": false,
229
- "special": false
230
- },
231
- {
232
- "id": 25,
233
- "content": "<extra_id_20>",
234
- "single_word": false,
235
- "lstrip": false,
236
- "rstrip": false,
237
- "normalized": false,
238
- "special": false
239
- },
240
- {
241
- "id": 26,
242
- "content": "<extra_id_21>",
243
- "single_word": false,
244
- "lstrip": false,
245
- "rstrip": false,
246
- "normalized": false,
247
- "special": false
248
- },
249
- {
250
- "id": 27,
251
- "content": "<extra_id_22>",
252
- "single_word": false,
253
- "lstrip": false,
254
- "rstrip": false,
255
- "normalized": false,
256
- "special": false
257
- },
258
- {
259
- "id": 28,
260
- "content": "<extra_id_23>",
261
- "single_word": false,
262
- "lstrip": false,
263
- "rstrip": false,
264
- "normalized": false,
265
- "special": false
266
- },
267
- {
268
- "id": 29,
269
- "content": "<extra_id_24>",
270
- "single_word": false,
271
- "lstrip": false,
272
- "rstrip": false,
273
- "normalized": false,
274
- "special": false
275
- },
276
- {
277
- "id": 30,
278
- "content": "<extra_id_25>",
279
- "single_word": false,
280
- "lstrip": false,
281
- "rstrip": false,
282
- "normalized": false,
283
- "special": false
284
- },
285
- {
286
- "id": 31,
287
- "content": "<extra_id_26>",
288
- "single_word": false,
289
- "lstrip": false,
290
- "rstrip": false,
291
- "normalized": false,
292
- "special": false
293
- },
294
- {
295
- "id": 32,
296
- "content": "<extra_id_27>",
297
- "single_word": false,
298
- "lstrip": false,
299
- "rstrip": false,
300
- "normalized": false,
301
- "special": false
302
- },
303
- {
304
- "id": 33,
305
- "content": "<extra_id_28>",
306
- "single_word": false,
307
- "lstrip": false,
308
- "rstrip": false,
309
- "normalized": false,
310
- "special": false
311
- },
312
- {
313
- "id": 34,
314
- "content": "<extra_id_29>",
315
- "single_word": false,
316
- "lstrip": false,
317
- "rstrip": false,
318
- "normalized": false,
319
- "special": false
320
- },
321
- {
322
- "id": 35,
323
- "content": "<extra_id_30>",
324
- "single_word": false,
325
- "lstrip": false,
326
- "rstrip": false,
327
- "normalized": false,
328
- "special": false
329
- },
330
- {
331
- "id": 36,
332
- "content": "<extra_id_31>",
333
- "single_word": false,
334
- "lstrip": false,
335
- "rstrip": false,
336
- "normalized": false,
337
- "special": false
338
- },
339
- {
340
- "id": 37,
341
- "content": "<extra_id_32>",
342
- "single_word": false,
343
- "lstrip": false,
344
- "rstrip": false,
345
- "normalized": false,
346
- "special": false
347
- },
348
- {
349
- "id": 38,
350
- "content": "<extra_id_33>",
351
- "single_word": false,
352
- "lstrip": false,
353
- "rstrip": false,
354
- "normalized": false,
355
- "special": false
356
- },
357
- {
358
- "id": 39,
359
- "content": "<extra_id_34>",
360
- "single_word": false,
361
- "lstrip": false,
362
- "rstrip": false,
363
- "normalized": false,
364
- "special": false
365
- },
366
- {
367
- "id": 40,
368
- "content": "<extra_id_35>",
369
- "single_word": false,
370
- "lstrip": false,
371
- "rstrip": false,
372
- "normalized": false,
373
- "special": false
374
- },
375
- {
376
- "id": 41,
377
- "content": "<extra_id_36>",
378
- "single_word": false,
379
- "lstrip": false,
380
- "rstrip": false,
381
- "normalized": false,
382
- "special": false
383
- },
384
- {
385
- "id": 42,
386
- "content": "<extra_id_37>",
387
- "single_word": false,
388
- "lstrip": false,
389
- "rstrip": false,
390
- "normalized": false,
391
- "special": false
392
- },
393
- {
394
- "id": 43,
395
- "content": "<extra_id_38>",
396
- "single_word": false,
397
- "lstrip": false,
398
- "rstrip": false,
399
- "normalized": false,
400
- "special": false
401
- },
402
- {
403
- "id": 44,
404
- "content": "<extra_id_39>",
405
- "single_word": false,
406
- "lstrip": false,
407
- "rstrip": false,
408
- "normalized": false,
409
- "special": false
410
- },
411
- {
412
- "id": 45,
413
- "content": "<extra_id_40>",
414
- "single_word": false,
415
- "lstrip": false,
416
- "rstrip": false,
417
- "normalized": false,
418
- "special": false
419
- },
420
- {
421
- "id": 46,
422
- "content": "<extra_id_41>",
423
- "single_word": false,
424
- "lstrip": false,
425
- "rstrip": false,
426
- "normalized": false,
427
- "special": false
428
- },
429
- {
430
- "id": 47,
431
- "content": "<extra_id_42>",
432
- "single_word": false,
433
- "lstrip": false,
434
- "rstrip": false,
435
- "normalized": false,
436
- "special": false
437
- },
438
- {
439
- "id": 48,
440
- "content": "<extra_id_43>",
441
- "single_word": false,
442
- "lstrip": false,
443
- "rstrip": false,
444
- "normalized": false,
445
- "special": false
446
- },
447
- {
448
- "id": 49,
449
- "content": "<extra_id_44>",
450
- "single_word": false,
451
- "lstrip": false,
452
- "rstrip": false,
453
- "normalized": false,
454
- "special": false
455
- },
456
- {
457
- "id": 50,
458
- "content": "<extra_id_45>",
459
- "single_word": false,
460
- "lstrip": false,
461
- "rstrip": false,
462
- "normalized": false,
463
- "special": false
464
- },
465
- {
466
- "id": 51,
467
- "content": "<extra_id_46>",
468
- "single_word": false,
469
- "lstrip": false,
470
- "rstrip": false,
471
- "normalized": false,
472
- "special": false
473
- },
474
- {
475
- "id": 52,
476
- "content": "<extra_id_47>",
477
- "single_word": false,
478
- "lstrip": false,
479
- "rstrip": false,
480
- "normalized": false,
481
- "special": false
482
- },
483
- {
484
- "id": 53,
485
- "content": "<extra_id_48>",
486
- "single_word": false,
487
- "lstrip": false,
488
- "rstrip": false,
489
- "normalized": false,
490
- "special": false
491
- },
492
- {
493
- "id": 54,
494
- "content": "<extra_id_49>",
495
- "single_word": false,
496
- "lstrip": false,
497
- "rstrip": false,
498
- "normalized": false,
499
- "special": false
500
- },
501
- {
502
- "id": 55,
503
- "content": "<extra_id_50>",
504
- "single_word": false,
505
- "lstrip": false,
506
- "rstrip": false,
507
- "normalized": false,
508
- "special": false
509
- },
510
- {
511
- "id": 56,
512
- "content": "<extra_id_51>",
513
- "single_word": false,
514
- "lstrip": false,
515
- "rstrip": false,
516
- "normalized": false,
517
- "special": false
518
- },
519
- {
520
- "id": 57,
521
- "content": "<extra_id_52>",
522
- "single_word": false,
523
- "lstrip": false,
524
- "rstrip": false,
525
- "normalized": false,
526
- "special": false
527
- },
528
- {
529
- "id": 58,
530
- "content": "<extra_id_53>",
531
- "single_word": false,
532
- "lstrip": false,
533
- "rstrip": false,
534
- "normalized": false,
535
- "special": false
536
- },
537
- {
538
- "id": 59,
539
- "content": "<extra_id_54>",
540
- "single_word": false,
541
- "lstrip": false,
542
- "rstrip": false,
543
- "normalized": false,
544
- "special": false
545
- },
546
- {
547
- "id": 60,
548
- "content": "<extra_id_55>",
549
- "single_word": false,
550
- "lstrip": false,
551
- "rstrip": false,
552
- "normalized": false,
553
- "special": false
554
- },
555
- {
556
- "id": 61,
557
- "content": "<extra_id_56>",
558
- "single_word": false,
559
- "lstrip": false,
560
- "rstrip": false,
561
- "normalized": false,
562
- "special": false
563
- },
564
- {
565
- "id": 62,
566
- "content": "<extra_id_57>",
567
- "single_word": false,
568
- "lstrip": false,
569
- "rstrip": false,
570
- "normalized": false,
571
- "special": false
572
- },
573
- {
574
- "id": 63,
575
- "content": "<extra_id_58>",
576
- "single_word": false,
577
- "lstrip": false,
578
- "rstrip": false,
579
- "normalized": false,
580
- "special": false
581
- },
582
- {
583
- "id": 64,
584
- "content": "<extra_id_59>",
585
- "single_word": false,
586
- "lstrip": false,
587
- "rstrip": false,
588
- "normalized": false,
589
- "special": false
590
- },
591
- {
592
- "id": 65,
593
- "content": "<extra_id_60>",
594
- "single_word": false,
595
- "lstrip": false,
596
- "rstrip": false,
597
- "normalized": false,
598
- "special": false
599
- },
600
- {
601
- "id": 66,
602
- "content": "<extra_id_61>",
603
- "single_word": false,
604
- "lstrip": false,
605
- "rstrip": false,
606
- "normalized": false,
607
- "special": false
608
- },
609
- {
610
- "id": 67,
611
- "content": "<extra_id_62>",
612
- "single_word": false,
613
- "lstrip": false,
614
- "rstrip": false,
615
- "normalized": false,
616
- "special": false
617
- },
618
- {
619
- "id": 68,
620
- "content": "<extra_id_63>",
621
- "single_word": false,
622
- "lstrip": false,
623
- "rstrip": false,
624
- "normalized": false,
625
- "special": false
626
- },
627
- {
628
- "id": 69,
629
- "content": "<extra_id_64>",
630
- "single_word": false,
631
- "lstrip": false,
632
- "rstrip": false,
633
- "normalized": false,
634
- "special": false
635
- },
636
- {
637
- "id": 70,
638
- "content": "<extra_id_65>",
639
- "single_word": false,
640
- "lstrip": false,
641
- "rstrip": false,
642
- "normalized": false,
643
- "special": false
644
- },
645
- {
646
- "id": 71,
647
- "content": "<extra_id_66>",
648
- "single_word": false,
649
- "lstrip": false,
650
- "rstrip": false,
651
- "normalized": false,
652
- "special": false
653
- },
654
- {
655
- "id": 72,
656
- "content": "<extra_id_67>",
657
- "single_word": false,
658
- "lstrip": false,
659
- "rstrip": false,
660
- "normalized": false,
661
- "special": false
662
- },
663
- {
664
- "id": 73,
665
- "content": "<extra_id_68>",
666
- "single_word": false,
667
- "lstrip": false,
668
- "rstrip": false,
669
- "normalized": false,
670
- "special": false
671
- },
672
- {
673
- "id": 74,
674
- "content": "<extra_id_69>",
675
- "single_word": false,
676
- "lstrip": false,
677
- "rstrip": false,
678
- "normalized": false,
679
- "special": false
680
- },
681
- {
682
- "id": 75,
683
- "content": "<extra_id_70>",
684
- "single_word": false,
685
- "lstrip": false,
686
- "rstrip": false,
687
- "normalized": false,
688
- "special": false
689
- },
690
- {
691
- "id": 76,
692
- "content": "<extra_id_71>",
693
- "single_word": false,
694
- "lstrip": false,
695
- "rstrip": false,
696
- "normalized": false,
697
- "special": false
698
- },
699
- {
700
- "id": 77,
701
- "content": "<extra_id_72>",
702
- "single_word": false,
703
- "lstrip": false,
704
- "rstrip": false,
705
- "normalized": false,
706
- "special": false
707
- },
708
- {
709
- "id": 78,
710
- "content": "<extra_id_73>",
711
- "single_word": false,
712
- "lstrip": false,
713
- "rstrip": false,
714
- "normalized": false,
715
- "special": false
716
- },
717
- {
718
- "id": 79,
719
- "content": "<extra_id_74>",
720
- "single_word": false,
721
- "lstrip": false,
722
- "rstrip": false,
723
- "normalized": false,
724
- "special": false
725
- },
726
- {
727
- "id": 80,
728
- "content": "<extra_id_75>",
729
- "single_word": false,
730
- "lstrip": false,
731
- "rstrip": false,
732
- "normalized": false,
733
- "special": false
734
- },
735
- {
736
- "id": 81,
737
- "content": "<extra_id_76>",
738
- "single_word": false,
739
- "lstrip": false,
740
- "rstrip": false,
741
- "normalized": false,
742
- "special": false
743
- },
744
- {
745
- "id": 82,
746
- "content": "<extra_id_77>",
747
- "single_word": false,
748
- "lstrip": false,
749
- "rstrip": false,
750
- "normalized": false,
751
- "special": false
752
- },
753
- {
754
- "id": 83,
755
- "content": "<extra_id_78>",
756
- "single_word": false,
757
- "lstrip": false,
758
- "rstrip": false,
759
- "normalized": false,
760
- "special": false
761
- },
762
- {
763
- "id": 84,
764
- "content": "<extra_id_79>",
765
- "single_word": false,
766
- "lstrip": false,
767
- "rstrip": false,
768
- "normalized": false,
769
- "special": false
770
- },
771
- {
772
- "id": 85,
773
- "content": "<extra_id_80>",
774
- "single_word": false,
775
- "lstrip": false,
776
- "rstrip": false,
777
- "normalized": false,
778
- "special": false
779
- },
780
- {
781
- "id": 86,
782
- "content": "<extra_id_81>",
783
- "single_word": false,
784
- "lstrip": false,
785
- "rstrip": false,
786
- "normalized": false,
787
- "special": false
788
- },
789
- {
790
- "id": 87,
791
- "content": "<extra_id_82>",
792
- "single_word": false,
793
- "lstrip": false,
794
- "rstrip": false,
795
- "normalized": false,
796
- "special": false
797
- },
798
- {
799
- "id": 88,
800
- "content": "<extra_id_83>",
801
- "single_word": false,
802
- "lstrip": false,
803
- "rstrip": false,
804
- "normalized": false,
805
- "special": false
806
- },
807
- {
808
- "id": 89,
809
- "content": "<extra_id_84>",
810
- "single_word": false,
811
- "lstrip": false,
812
- "rstrip": false,
813
- "normalized": false,
814
- "special": false
815
- },
816
- {
817
- "id": 90,
818
- "content": "<extra_id_85>",
819
- "single_word": false,
820
- "lstrip": false,
821
- "rstrip": false,
822
- "normalized": false,
823
- "special": false
824
- },
825
- {
826
- "id": 91,
827
- "content": "<extra_id_86>",
828
- "single_word": false,
829
- "lstrip": false,
830
- "rstrip": false,
831
- "normalized": false,
832
- "special": false
833
- },
834
- {
835
- "id": 92,
836
- "content": "<extra_id_87>",
837
- "single_word": false,
838
- "lstrip": false,
839
- "rstrip": false,
840
- "normalized": false,
841
- "special": false
842
- },
843
- {
844
- "id": 93,
845
- "content": "<extra_id_88>",
846
- "single_word": false,
847
- "lstrip": false,
848
- "rstrip": false,
849
- "normalized": false,
850
- "special": false
851
- },
852
- {
853
- "id": 94,
854
- "content": "<extra_id_89>",
855
- "single_word": false,
856
- "lstrip": false,
857
- "rstrip": false,
858
- "normalized": false,
859
- "special": false
860
- },
861
- {
862
- "id": 95,
863
- "content": "<extra_id_90>",
864
- "single_word": false,
865
- "lstrip": false,
866
- "rstrip": false,
867
- "normalized": false,
868
- "special": false
869
- },
870
- {
871
- "id": 96,
872
- "content": "<extra_id_91>",
873
- "single_word": false,
874
- "lstrip": false,
875
- "rstrip": false,
876
- "normalized": false,
877
- "special": false
878
- },
879
- {
880
- "id": 97,
881
- "content": "<extra_id_92>",
882
- "single_word": false,
883
- "lstrip": false,
884
- "rstrip": false,
885
- "normalized": false,
886
- "special": false
887
- },
888
- {
889
- "id": 98,
890
- "content": "<extra_id_93>",
891
- "single_word": false,
892
- "lstrip": false,
893
- "rstrip": false,
894
- "normalized": false,
895
- "special": false
896
- },
897
- {
898
- "id": 99,
899
- "content": "<extra_id_94>",
900
- "single_word": false,
901
- "lstrip": false,
902
- "rstrip": false,
903
- "normalized": false,
904
- "special": false
905
- },
906
- {
907
- "id": 100,
908
- "content": "<extra_id_95>",
909
- "single_word": false,
910
- "lstrip": false,
911
- "rstrip": false,
912
- "normalized": false,
913
- "special": false
914
- },
915
- {
916
- "id": 101,
917
- "content": "<extra_id_96>",
918
- "single_word": false,
919
- "lstrip": false,
920
- "rstrip": false,
921
- "normalized": false,
922
- "special": false
923
- },
924
- {
925
- "id": 102,
926
- "content": "<extra_id_97>",
927
- "single_word": false,
928
- "lstrip": false,
929
- "rstrip": false,
930
- "normalized": false,
931
- "special": false
932
- },
933
- {
934
- "id": 103,
935
- "content": "<extra_id_98>",
936
- "single_word": false,
937
- "lstrip": false,
938
- "rstrip": false,
939
- "normalized": false,
940
- "special": false
941
- },
942
- {
943
- "id": 104,
944
- "content": "<extra_id_99>",
945
- "single_word": false,
946
- "lstrip": false,
947
- "rstrip": false,
948
- "normalized": false,
949
- "special": false
950
- },
951
- {
952
- "id": 105,
953
- "content": "<extra_id_100>",
954
- "single_word": false,
955
- "lstrip": false,
956
- "rstrip": false,
957
- "normalized": false,
958
- "special": false
959
- },
960
- {
961
- "id": 106,
962
- "content": "<extra_id_101>",
963
- "single_word": false,
964
- "lstrip": false,
965
- "rstrip": false,
966
- "normalized": false,
967
- "special": false
968
- },
969
- {
970
- "id": 107,
971
- "content": "<extra_id_102>",
972
- "single_word": false,
973
- "lstrip": false,
974
- "rstrip": false,
975
- "normalized": false,
976
- "special": false
977
- },
978
- {
979
- "id": 108,
980
- "content": "<extra_id_103>",
981
- "single_word": false,
982
- "lstrip": false,
983
- "rstrip": false,
984
- "normalized": false,
985
- "special": false
986
- },
987
- {
988
- "id": 109,
989
- "content": "<extra_id_104>",
990
- "single_word": false,
991
- "lstrip": false,
992
- "rstrip": false,
993
- "normalized": false,
994
- "special": false
995
- },
996
- {
997
- "id": 110,
998
- "content": "<extra_id_105>",
999
- "single_word": false,
1000
- "lstrip": false,
1001
- "rstrip": false,
1002
- "normalized": false,
1003
- "special": false
1004
- },
1005
- {
1006
- "id": 111,
1007
- "content": "<extra_id_106>",
1008
- "single_word": false,
1009
- "lstrip": false,
1010
- "rstrip": false,
1011
- "normalized": false,
1012
- "special": false
1013
- },
1014
- {
1015
- "id": 112,
1016
- "content": "<extra_id_107>",
1017
- "single_word": false,
1018
- "lstrip": false,
1019
- "rstrip": false,
1020
- "normalized": false,
1021
- "special": false
1022
- },
1023
- {
1024
- "id": 113,
1025
- "content": "<extra_id_108>",
1026
- "single_word": false,
1027
- "lstrip": false,
1028
- "rstrip": false,
1029
- "normalized": false,
1030
- "special": false
1031
- },
1032
- {
1033
- "id": 114,
1034
- "content": "<extra_id_109>",
1035
- "single_word": false,
1036
- "lstrip": false,
1037
- "rstrip": false,
1038
- "normalized": false,
1039
- "special": false
1040
- },
1041
- {
1042
- "id": 115,
1043
- "content": "<extra_id_110>",
1044
- "single_word": false,
1045
- "lstrip": false,
1046
- "rstrip": false,
1047
- "normalized": false,
1048
- "special": false
1049
- },
1050
- {
1051
- "id": 116,
1052
- "content": "<extra_id_111>",
1053
- "single_word": false,
1054
- "lstrip": false,
1055
- "rstrip": false,
1056
- "normalized": false,
1057
- "special": false
1058
- },
1059
- {
1060
- "id": 117,
1061
- "content": "<extra_id_112>",
1062
- "single_word": false,
1063
- "lstrip": false,
1064
- "rstrip": false,
1065
- "normalized": false,
1066
- "special": false
1067
- },
1068
- {
1069
- "id": 118,
1070
- "content": "<extra_id_113>",
1071
- "single_word": false,
1072
- "lstrip": false,
1073
- "rstrip": false,
1074
- "normalized": false,
1075
- "special": false
1076
- },
1077
- {
1078
- "id": 119,
1079
- "content": "<extra_id_114>",
1080
- "single_word": false,
1081
- "lstrip": false,
1082
- "rstrip": false,
1083
- "normalized": false,
1084
- "special": false
1085
- },
1086
- {
1087
- "id": 120,
1088
- "content": "<extra_id_115>",
1089
- "single_word": false,
1090
- "lstrip": false,
1091
- "rstrip": false,
1092
- "normalized": false,
1093
- "special": false
1094
- },
1095
- {
1096
- "id": 121,
1097
- "content": "<extra_id_116>",
1098
- "single_word": false,
1099
- "lstrip": false,
1100
- "rstrip": false,
1101
- "normalized": false,
1102
- "special": false
1103
- },
1104
- {
1105
- "id": 122,
1106
- "content": "<extra_id_117>",
1107
- "single_word": false,
1108
- "lstrip": false,
1109
- "rstrip": false,
1110
- "normalized": false,
1111
- "special": false
1112
- },
1113
- {
1114
- "id": 123,
1115
- "content": "<extra_id_118>",
1116
- "single_word": false,
1117
- "lstrip": false,
1118
- "rstrip": false,
1119
- "normalized": false,
1120
- "special": false
1121
- },
1122
- {
1123
- "id": 124,
1124
- "content": "<extra_id_119>",
1125
- "single_word": false,
1126
- "lstrip": false,
1127
- "rstrip": false,
1128
- "normalized": false,
1129
- "special": false
1130
- },
1131
- {
1132
- "id": 125,
1133
- "content": "<extra_id_120>",
1134
- "single_word": false,
1135
- "lstrip": false,
1136
- "rstrip": false,
1137
- "normalized": false,
1138
- "special": false
1139
- },
1140
- {
1141
- "id": 126,
1142
- "content": "<extra_id_121>",
1143
- "single_word": false,
1144
- "lstrip": false,
1145
- "rstrip": false,
1146
- "normalized": false,
1147
- "special": false
1148
- },
1149
- {
1150
- "id": 127,
1151
- "content": "<extra_id_122>",
1152
- "single_word": false,
1153
- "lstrip": false,
1154
- "rstrip": false,
1155
- "normalized": false,
1156
- "special": false
1157
- },
1158
- {
1159
- "id": 128,
1160
- "content": "<extra_id_123>",
1161
- "single_word": false,
1162
- "lstrip": false,
1163
- "rstrip": false,
1164
- "normalized": false,
1165
- "special": false
1166
- },
1167
- {
1168
- "id": 129,
1169
- "content": "<extra_id_124>",
1170
- "single_word": false,
1171
- "lstrip": false,
1172
- "rstrip": false,
1173
- "normalized": false,
1174
- "special": false
1175
- },
1176
- {
1177
- "id": 130,
1178
- "content": "<extra_id_125>",
1179
- "single_word": false,
1180
- "lstrip": false,
1181
- "rstrip": false,
1182
- "normalized": false,
1183
- "special": false
1184
- },
1185
- {
1186
- "id": 131,
1187
- "content": "<extra_id_126>",
1188
- "single_word": false,
1189
- "lstrip": false,
1190
- "rstrip": false,
1191
- "normalized": false,
1192
- "special": false
1193
- },
1194
- {
1195
- "id": 132,
1196
- "content": "<extra_id_127>",
1197
- "single_word": false,
1198
- "lstrip": false,
1199
- "rstrip": false,
1200
- "normalized": false,
1201
- "special": false
1202
- },
1203
- {
1204
- "id": 133,
1205
- "content": "<extra_id_128>",
1206
- "single_word": false,
1207
- "lstrip": false,
1208
- "rstrip": false,
1209
- "normalized": false,
1210
- "special": false
1211
- },
1212
- {
1213
- "id": 134,
1214
- "content": "<extra_id_129>",
1215
- "single_word": false,
1216
- "lstrip": false,
1217
- "rstrip": false,
1218
- "normalized": false,
1219
- "special": false
1220
- },
1221
- {
1222
- "id": 135,
1223
- "content": "<extra_id_130>",
1224
- "single_word": false,
1225
- "lstrip": false,
1226
- "rstrip": false,
1227
- "normalized": false,
1228
- "special": false
1229
- },
1230
- {
1231
- "id": 136,
1232
- "content": "<extra_id_131>",
1233
- "single_word": false,
1234
- "lstrip": false,
1235
- "rstrip": false,
1236
- "normalized": false,
1237
- "special": false
1238
- },
1239
- {
1240
- "id": 137,
1241
- "content": "<extra_id_132>",
1242
- "single_word": false,
1243
- "lstrip": false,
1244
- "rstrip": false,
1245
- "normalized": false,
1246
- "special": false
1247
- },
1248
- {
1249
- "id": 138,
1250
- "content": "<extra_id_133>",
1251
- "single_word": false,
1252
- "lstrip": false,
1253
- "rstrip": false,
1254
- "normalized": false,
1255
- "special": false
1256
- },
1257
- {
1258
- "id": 139,
1259
- "content": "<extra_id_134>",
1260
- "single_word": false,
1261
- "lstrip": false,
1262
- "rstrip": false,
1263
- "normalized": false,
1264
- "special": false
1265
- },
1266
- {
1267
- "id": 140,
1268
- "content": "<extra_id_135>",
1269
- "single_word": false,
1270
- "lstrip": false,
1271
- "rstrip": false,
1272
- "normalized": false,
1273
- "special": false
1274
- },
1275
- {
1276
- "id": 141,
1277
- "content": "<extra_id_136>",
1278
- "single_word": false,
1279
- "lstrip": false,
1280
- "rstrip": false,
1281
- "normalized": false,
1282
- "special": false
1283
- },
1284
- {
1285
- "id": 142,
1286
- "content": "<extra_id_137>",
1287
- "single_word": false,
1288
- "lstrip": false,
1289
- "rstrip": false,
1290
- "normalized": false,
1291
- "special": false
1292
- },
1293
- {
1294
- "id": 143,
1295
- "content": "<extra_id_138>",
1296
- "single_word": false,
1297
- "lstrip": false,
1298
- "rstrip": false,
1299
- "normalized": false,
1300
- "special": false
1301
- },
1302
- {
1303
- "id": 144,
1304
- "content": "<extra_id_139>",
1305
- "single_word": false,
1306
- "lstrip": false,
1307
- "rstrip": false,
1308
- "normalized": false,
1309
- "special": false
1310
- },
1311
- {
1312
- "id": 145,
1313
- "content": "<extra_id_140>",
1314
- "single_word": false,
1315
- "lstrip": false,
1316
- "rstrip": false,
1317
- "normalized": false,
1318
- "special": false
1319
- },
1320
- {
1321
- "id": 146,
1322
- "content": "<extra_id_141>",
1323
- "single_word": false,
1324
- "lstrip": false,
1325
- "rstrip": false,
1326
- "normalized": false,
1327
- "special": false
1328
- },
1329
- {
1330
- "id": 147,
1331
- "content": "<extra_id_142>",
1332
- "single_word": false,
1333
- "lstrip": false,
1334
- "rstrip": false,
1335
- "normalized": false,
1336
- "special": false
1337
- },
1338
- {
1339
- "id": 148,
1340
- "content": "<extra_id_143>",
1341
- "single_word": false,
1342
- "lstrip": false,
1343
- "rstrip": false,
1344
- "normalized": false,
1345
- "special": false
1346
- },
1347
- {
1348
- "id": 149,
1349
- "content": "<extra_id_144>",
1350
- "single_word": false,
1351
- "lstrip": false,
1352
- "rstrip": false,
1353
- "normalized": false,
1354
- "special": false
1355
- },
1356
- {
1357
- "id": 150,
1358
- "content": "<extra_id_145>",
1359
- "single_word": false,
1360
- "lstrip": false,
1361
- "rstrip": false,
1362
- "normalized": false,
1363
- "special": false
1364
- },
1365
- {
1366
- "id": 151,
1367
- "content": "<extra_id_146>",
1368
- "single_word": false,
1369
- "lstrip": false,
1370
- "rstrip": false,
1371
- "normalized": false,
1372
- "special": false
1373
- },
1374
- {
1375
- "id": 152,
1376
- "content": "<extra_id_147>",
1377
- "single_word": false,
1378
- "lstrip": false,
1379
- "rstrip": false,
1380
- "normalized": false,
1381
- "special": false
1382
- },
1383
- {
1384
- "id": 153,
1385
- "content": "<extra_id_148>",
1386
- "single_word": false,
1387
- "lstrip": false,
1388
- "rstrip": false,
1389
- "normalized": false,
1390
- "special": false
1391
- },
1392
- {
1393
- "id": 154,
1394
- "content": "<extra_id_149>",
1395
- "single_word": false,
1396
- "lstrip": false,
1397
- "rstrip": false,
1398
- "normalized": false,
1399
- "special": false
1400
- },
1401
- {
1402
- "id": 155,
1403
- "content": "<extra_id_150>",
1404
- "single_word": false,
1405
- "lstrip": false,
1406
- "rstrip": false,
1407
- "normalized": false,
1408
- "special": false
1409
- },
1410
- {
1411
- "id": 156,
1412
- "content": "<extra_id_151>",
1413
- "single_word": false,
1414
- "lstrip": false,
1415
- "rstrip": false,
1416
- "normalized": false,
1417
- "special": false
1418
- },
1419
- {
1420
- "id": 157,
1421
- "content": "<extra_id_152>",
1422
- "single_word": false,
1423
- "lstrip": false,
1424
- "rstrip": false,
1425
- "normalized": false,
1426
- "special": false
1427
- },
1428
- {
1429
- "id": 158,
1430
- "content": "<extra_id_153>",
1431
- "single_word": false,
1432
- "lstrip": false,
1433
- "rstrip": false,
1434
- "normalized": false,
1435
- "special": false
1436
- },
1437
- {
1438
- "id": 159,
1439
- "content": "<extra_id_154>",
1440
- "single_word": false,
1441
- "lstrip": false,
1442
- "rstrip": false,
1443
- "normalized": false,
1444
- "special": false
1445
- },
1446
- {
1447
- "id": 160,
1448
- "content": "<extra_id_155>",
1449
- "single_word": false,
1450
- "lstrip": false,
1451
- "rstrip": false,
1452
- "normalized": false,
1453
- "special": false
1454
- },
1455
- {
1456
- "id": 161,
1457
- "content": "<extra_id_156>",
1458
- "single_word": false,
1459
- "lstrip": false,
1460
- "rstrip": false,
1461
- "normalized": false,
1462
- "special": false
1463
- },
1464
- {
1465
- "id": 162,
1466
- "content": "<extra_id_157>",
1467
- "single_word": false,
1468
- "lstrip": false,
1469
- "rstrip": false,
1470
- "normalized": false,
1471
- "special": false
1472
- },
1473
- {
1474
- "id": 163,
1475
- "content": "<extra_id_158>",
1476
- "single_word": false,
1477
- "lstrip": false,
1478
- "rstrip": false,
1479
- "normalized": false,
1480
- "special": false
1481
- },
1482
- {
1483
- "id": 164,
1484
- "content": "<extra_id_159>",
1485
- "single_word": false,
1486
- "lstrip": false,
1487
- "rstrip": false,
1488
- "normalized": false,
1489
- "special": false
1490
- },
1491
- {
1492
- "id": 165,
1493
- "content": "<extra_id_160>",
1494
- "single_word": false,
1495
- "lstrip": false,
1496
- "rstrip": false,
1497
- "normalized": false,
1498
- "special": false
1499
- },
1500
- {
1501
- "id": 166,
1502
- "content": "<extra_id_161>",
1503
- "single_word": false,
1504
- "lstrip": false,
1505
- "rstrip": false,
1506
- "normalized": false,
1507
- "special": false
1508
- },
1509
- {
1510
- "id": 167,
1511
- "content": "<extra_id_162>",
1512
- "single_word": false,
1513
- "lstrip": false,
1514
- "rstrip": false,
1515
- "normalized": false,
1516
- "special": false
1517
- },
1518
- {
1519
- "id": 168,
1520
- "content": "<extra_id_163>",
1521
- "single_word": false,
1522
- "lstrip": false,
1523
- "rstrip": false,
1524
- "normalized": false,
1525
- "special": false
1526
- },
1527
- {
1528
- "id": 169,
1529
- "content": "<extra_id_164>",
1530
- "single_word": false,
1531
- "lstrip": false,
1532
- "rstrip": false,
1533
- "normalized": false,
1534
- "special": false
1535
- },
1536
- {
1537
- "id": 170,
1538
- "content": "<extra_id_165>",
1539
- "single_word": false,
1540
- "lstrip": false,
1541
- "rstrip": false,
1542
- "normalized": false,
1543
- "special": false
1544
- },
1545
- {
1546
- "id": 171,
1547
- "content": "<extra_id_166>",
1548
- "single_word": false,
1549
- "lstrip": false,
1550
- "rstrip": false,
1551
- "normalized": false,
1552
- "special": false
1553
- },
1554
- {
1555
- "id": 172,
1556
- "content": "<extra_id_167>",
1557
- "single_word": false,
1558
- "lstrip": false,
1559
- "rstrip": false,
1560
- "normalized": false,
1561
- "special": false
1562
- },
1563
- {
1564
- "id": 173,
1565
- "content": "<extra_id_168>",
1566
- "single_word": false,
1567
- "lstrip": false,
1568
- "rstrip": false,
1569
- "normalized": false,
1570
- "special": false
1571
- },
1572
- {
1573
- "id": 174,
1574
- "content": "<extra_id_169>",
1575
- "single_word": false,
1576
- "lstrip": false,
1577
- "rstrip": false,
1578
- "normalized": false,
1579
- "special": false
1580
- },
1581
- {
1582
- "id": 175,
1583
- "content": "<extra_id_170>",
1584
- "single_word": false,
1585
- "lstrip": false,
1586
- "rstrip": false,
1587
- "normalized": false,
1588
- "special": false
1589
- },
1590
- {
1591
- "id": 176,
1592
- "content": "<extra_id_171>",
1593
- "single_word": false,
1594
- "lstrip": false,
1595
- "rstrip": false,
1596
- "normalized": false,
1597
- "special": false
1598
- },
1599
- {
1600
- "id": 177,
1601
- "content": "<extra_id_172>",
1602
- "single_word": false,
1603
- "lstrip": false,
1604
- "rstrip": false,
1605
- "normalized": false,
1606
- "special": false
1607
- },
1608
- {
1609
- "id": 178,
1610
- "content": "<extra_id_173>",
1611
- "single_word": false,
1612
- "lstrip": false,
1613
- "rstrip": false,
1614
- "normalized": false,
1615
- "special": false
1616
- },
1617
- {
1618
- "id": 179,
1619
- "content": "<extra_id_174>",
1620
- "single_word": false,
1621
- "lstrip": false,
1622
- "rstrip": false,
1623
- "normalized": false,
1624
- "special": false
1625
- },
1626
- {
1627
- "id": 180,
1628
- "content": "<extra_id_175>",
1629
- "single_word": false,
1630
- "lstrip": false,
1631
- "rstrip": false,
1632
- "normalized": false,
1633
- "special": false
1634
- },
1635
- {
1636
- "id": 181,
1637
- "content": "<extra_id_176>",
1638
- "single_word": false,
1639
- "lstrip": false,
1640
- "rstrip": false,
1641
- "normalized": false,
1642
- "special": false
1643
- },
1644
- {
1645
- "id": 182,
1646
- "content": "<extra_id_177>",
1647
- "single_word": false,
1648
- "lstrip": false,
1649
- "rstrip": false,
1650
- "normalized": false,
1651
- "special": false
1652
- },
1653
- {
1654
- "id": 183,
1655
- "content": "<extra_id_178>",
1656
- "single_word": false,
1657
- "lstrip": false,
1658
- "rstrip": false,
1659
- "normalized": false,
1660
- "special": false
1661
- },
1662
- {
1663
- "id": 184,
1664
- "content": "<extra_id_179>",
1665
- "single_word": false,
1666
- "lstrip": false,
1667
- "rstrip": false,
1668
- "normalized": false,
1669
- "special": false
1670
- },
1671
- {
1672
- "id": 185,
1673
- "content": "<extra_id_180>",
1674
- "single_word": false,
1675
- "lstrip": false,
1676
- "rstrip": false,
1677
- "normalized": false,
1678
- "special": false
1679
- },
1680
- {
1681
- "id": 186,
1682
- "content": "<extra_id_181>",
1683
- "single_word": false,
1684
- "lstrip": false,
1685
- "rstrip": false,
1686
- "normalized": false,
1687
- "special": false
1688
- },
1689
- {
1690
- "id": 187,
1691
- "content": "<extra_id_182>",
1692
- "single_word": false,
1693
- "lstrip": false,
1694
- "rstrip": false,
1695
- "normalized": false,
1696
- "special": false
1697
- },
1698
- {
1699
- "id": 188,
1700
- "content": "<extra_id_183>",
1701
- "single_word": false,
1702
- "lstrip": false,
1703
- "rstrip": false,
1704
- "normalized": false,
1705
- "special": false
1706
- },
1707
- {
1708
- "id": 189,
1709
- "content": "<extra_id_184>",
1710
- "single_word": false,
1711
- "lstrip": false,
1712
- "rstrip": false,
1713
- "normalized": false,
1714
- "special": false
1715
- },
1716
- {
1717
- "id": 190,
1718
- "content": "<extra_id_185>",
1719
- "single_word": false,
1720
- "lstrip": false,
1721
- "rstrip": false,
1722
- "normalized": false,
1723
- "special": false
1724
- },
1725
- {
1726
- "id": 191,
1727
- "content": "<extra_id_186>",
1728
- "single_word": false,
1729
- "lstrip": false,
1730
- "rstrip": false,
1731
- "normalized": false,
1732
- "special": false
1733
- },
1734
- {
1735
- "id": 192,
1736
- "content": "<extra_id_187>",
1737
- "single_word": false,
1738
- "lstrip": false,
1739
- "rstrip": false,
1740
- "normalized": false,
1741
- "special": false
1742
- },
1743
- {
1744
- "id": 193,
1745
- "content": "<extra_id_188>",
1746
- "single_word": false,
1747
- "lstrip": false,
1748
- "rstrip": false,
1749
- "normalized": false,
1750
- "special": false
1751
- },
1752
- {
1753
- "id": 194,
1754
- "content": "<extra_id_189>",
1755
- "single_word": false,
1756
- "lstrip": false,
1757
- "rstrip": false,
1758
- "normalized": false,
1759
- "special": false
1760
- },
1761
- {
1762
- "id": 195,
1763
- "content": "<extra_id_190>",
1764
- "single_word": false,
1765
- "lstrip": false,
1766
- "rstrip": false,
1767
- "normalized": false,
1768
- "special": false
1769
- },
1770
- {
1771
- "id": 196,
1772
- "content": "<extra_id_191>",
1773
- "single_word": false,
1774
- "lstrip": false,
1775
- "rstrip": false,
1776
- "normalized": false,
1777
- "special": false
1778
- },
1779
- {
1780
- "id": 197,
1781
- "content": "<extra_id_192>",
1782
- "single_word": false,
1783
- "lstrip": false,
1784
- "rstrip": false,
1785
- "normalized": false,
1786
- "special": false
1787
- },
1788
- {
1789
- "id": 198,
1790
- "content": "<extra_id_193>",
1791
- "single_word": false,
1792
- "lstrip": false,
1793
- "rstrip": false,
1794
- "normalized": false,
1795
- "special": false
1796
- },
1797
- {
1798
- "id": 199,
1799
- "content": "<extra_id_194>",
1800
- "single_word": false,
1801
- "lstrip": false,
1802
- "rstrip": false,
1803
- "normalized": false,
1804
- "special": false
1805
- },
1806
- {
1807
- "id": 200,
1808
- "content": "<extra_id_195>",
1809
- "single_word": false,
1810
- "lstrip": false,
1811
- "rstrip": false,
1812
- "normalized": false,
1813
- "special": false
1814
- },
1815
- {
1816
- "id": 201,
1817
- "content": "<extra_id_196>",
1818
- "single_word": false,
1819
- "lstrip": false,
1820
- "rstrip": false,
1821
- "normalized": false,
1822
- "special": false
1823
- },
1824
- {
1825
- "id": 202,
1826
- "content": "<extra_id_197>",
1827
- "single_word": false,
1828
- "lstrip": false,
1829
- "rstrip": false,
1830
- "normalized": false,
1831
- "special": false
1832
- },
1833
- {
1834
- "id": 203,
1835
- "content": "<extra_id_198>",
1836
- "single_word": false,
1837
- "lstrip": false,
1838
- "rstrip": false,
1839
- "normalized": false,
1840
- "special": false
1841
- },
1842
- {
1843
- "id": 204,
1844
- "content": "<extra_id_199>",
1845
- "single_word": false,
1846
- "lstrip": false,
1847
- "rstrip": false,
1848
- "normalized": false,
1849
- "special": false
1850
- },
1851
- {
1852
- "id": 205,
1853
- "content": "<extra_id_200>",
1854
- "single_word": false,
1855
- "lstrip": false,
1856
- "rstrip": false,
1857
- "normalized": false,
1858
- "special": false
1859
- },
1860
- {
1861
- "id": 206,
1862
- "content": "<extra_id_201>",
1863
- "single_word": false,
1864
- "lstrip": false,
1865
- "rstrip": false,
1866
- "normalized": false,
1867
- "special": false
1868
- },
1869
- {
1870
- "id": 207,
1871
- "content": "<extra_id_202>",
1872
- "single_word": false,
1873
- "lstrip": false,
1874
- "rstrip": false,
1875
- "normalized": false,
1876
- "special": false
1877
- },
1878
- {
1879
- "id": 208,
1880
- "content": "<extra_id_203>",
1881
- "single_word": false,
1882
- "lstrip": false,
1883
- "rstrip": false,
1884
- "normalized": false,
1885
- "special": false
1886
- },
1887
- {
1888
- "id": 209,
1889
- "content": "<extra_id_204>",
1890
- "single_word": false,
1891
- "lstrip": false,
1892
- "rstrip": false,
1893
- "normalized": false,
1894
- "special": false
1895
- },
1896
- {
1897
- "id": 210,
1898
- "content": "<extra_id_205>",
1899
- "single_word": false,
1900
- "lstrip": false,
1901
- "rstrip": false,
1902
- "normalized": false,
1903
- "special": false
1904
- },
1905
- {
1906
- "id": 211,
1907
- "content": "<extra_id_206>",
1908
- "single_word": false,
1909
- "lstrip": false,
1910
- "rstrip": false,
1911
- "normalized": false,
1912
- "special": false
1913
- },
1914
- {
1915
- "id": 212,
1916
- "content": "<extra_id_207>",
1917
- "single_word": false,
1918
- "lstrip": false,
1919
- "rstrip": false,
1920
- "normalized": false,
1921
- "special": false
1922
- },
1923
- {
1924
- "id": 213,
1925
- "content": "<extra_id_208>",
1926
- "single_word": false,
1927
- "lstrip": false,
1928
- "rstrip": false,
1929
- "normalized": false,
1930
- "special": false
1931
- },
1932
- {
1933
- "id": 214,
1934
- "content": "<extra_id_209>",
1935
- "single_word": false,
1936
- "lstrip": false,
1937
- "rstrip": false,
1938
- "normalized": false,
1939
- "special": false
1940
- },
1941
- {
1942
- "id": 215,
1943
- "content": "<extra_id_210>",
1944
- "single_word": false,
1945
- "lstrip": false,
1946
- "rstrip": false,
1947
- "normalized": false,
1948
- "special": false
1949
- },
1950
- {
1951
- "id": 216,
1952
- "content": "<extra_id_211>",
1953
- "single_word": false,
1954
- "lstrip": false,
1955
- "rstrip": false,
1956
- "normalized": false,
1957
- "special": false
1958
- },
1959
- {
1960
- "id": 217,
1961
- "content": "<extra_id_212>",
1962
- "single_word": false,
1963
- "lstrip": false,
1964
- "rstrip": false,
1965
- "normalized": false,
1966
- "special": false
1967
- },
1968
- {
1969
- "id": 218,
1970
- "content": "<extra_id_213>",
1971
- "single_word": false,
1972
- "lstrip": false,
1973
- "rstrip": false,
1974
- "normalized": false,
1975
- "special": false
1976
- },
1977
- {
1978
- "id": 219,
1979
- "content": "<extra_id_214>",
1980
- "single_word": false,
1981
- "lstrip": false,
1982
- "rstrip": false,
1983
- "normalized": false,
1984
- "special": false
1985
- },
1986
- {
1987
- "id": 220,
1988
- "content": "<extra_id_215>",
1989
- "single_word": false,
1990
- "lstrip": false,
1991
- "rstrip": false,
1992
- "normalized": false,
1993
- "special": false
1994
- },
1995
- {
1996
- "id": 221,
1997
- "content": "<extra_id_216>",
1998
- "single_word": false,
1999
- "lstrip": false,
2000
- "rstrip": false,
2001
- "normalized": false,
2002
- "special": false
2003
- },
2004
- {
2005
- "id": 222,
2006
- "content": "<extra_id_217>",
2007
- "single_word": false,
2008
- "lstrip": false,
2009
- "rstrip": false,
2010
- "normalized": false,
2011
- "special": false
2012
- },
2013
- {
2014
- "id": 223,
2015
- "content": "<extra_id_218>",
2016
- "single_word": false,
2017
- "lstrip": false,
2018
- "rstrip": false,
2019
- "normalized": false,
2020
- "special": false
2021
- },
2022
- {
2023
- "id": 224,
2024
- "content": "<extra_id_219>",
2025
- "single_word": false,
2026
- "lstrip": false,
2027
- "rstrip": false,
2028
- "normalized": false,
2029
- "special": false
2030
- },
2031
- {
2032
- "id": 225,
2033
- "content": "<extra_id_220>",
2034
- "single_word": false,
2035
- "lstrip": false,
2036
- "rstrip": false,
2037
- "normalized": false,
2038
- "special": false
2039
- },
2040
- {
2041
- "id": 226,
2042
- "content": "<extra_id_221>",
2043
- "single_word": false,
2044
- "lstrip": false,
2045
- "rstrip": false,
2046
- "normalized": false,
2047
- "special": false
2048
- },
2049
- {
2050
- "id": 227,
2051
- "content": "<extra_id_222>",
2052
- "single_word": false,
2053
- "lstrip": false,
2054
- "rstrip": false,
2055
- "normalized": false,
2056
- "special": false
2057
- },
2058
- {
2059
- "id": 228,
2060
- "content": "<extra_id_223>",
2061
- "single_word": false,
2062
- "lstrip": false,
2063
- "rstrip": false,
2064
- "normalized": false,
2065
- "special": false
2066
- },
2067
- {
2068
- "id": 229,
2069
- "content": "<extra_id_224>",
2070
- "single_word": false,
2071
- "lstrip": false,
2072
- "rstrip": false,
2073
- "normalized": false,
2074
- "special": false
2075
- },
2076
- {
2077
- "id": 230,
2078
- "content": "<extra_id_225>",
2079
- "single_word": false,
2080
- "lstrip": false,
2081
- "rstrip": false,
2082
- "normalized": false,
2083
- "special": false
2084
- },
2085
- {
2086
- "id": 231,
2087
- "content": "<extra_id_226>",
2088
- "single_word": false,
2089
- "lstrip": false,
2090
- "rstrip": false,
2091
- "normalized": false,
2092
- "special": false
2093
- },
2094
- {
2095
- "id": 232,
2096
- "content": "<extra_id_227>",
2097
- "single_word": false,
2098
- "lstrip": false,
2099
- "rstrip": false,
2100
- "normalized": false,
2101
- "special": false
2102
- },
2103
- {
2104
- "id": 233,
2105
- "content": "<extra_id_228>",
2106
- "single_word": false,
2107
- "lstrip": false,
2108
- "rstrip": false,
2109
- "normalized": false,
2110
- "special": false
2111
- },
2112
- {
2113
- "id": 234,
2114
- "content": "<extra_id_229>",
2115
- "single_word": false,
2116
- "lstrip": false,
2117
- "rstrip": false,
2118
- "normalized": false,
2119
- "special": false
2120
- },
2121
- {
2122
- "id": 235,
2123
- "content": "<extra_id_230>",
2124
- "single_word": false,
2125
- "lstrip": false,
2126
- "rstrip": false,
2127
- "normalized": false,
2128
- "special": false
2129
- },
2130
- {
2131
- "id": 236,
2132
- "content": "<extra_id_231>",
2133
- "single_word": false,
2134
- "lstrip": false,
2135
- "rstrip": false,
2136
- "normalized": false,
2137
- "special": false
2138
- },
2139
- {
2140
- "id": 237,
2141
- "content": "<extra_id_232>",
2142
- "single_word": false,
2143
- "lstrip": false,
2144
- "rstrip": false,
2145
- "normalized": false,
2146
- "special": false
2147
- },
2148
- {
2149
- "id": 238,
2150
- "content": "<extra_id_233>",
2151
- "single_word": false,
2152
- "lstrip": false,
2153
- "rstrip": false,
2154
- "normalized": false,
2155
- "special": false
2156
- },
2157
- {
2158
- "id": 239,
2159
- "content": "<extra_id_234>",
2160
- "single_word": false,
2161
- "lstrip": false,
2162
- "rstrip": false,
2163
- "normalized": false,
2164
- "special": false
2165
- },
2166
- {
2167
- "id": 240,
2168
- "content": "<extra_id_235>",
2169
- "single_word": false,
2170
- "lstrip": false,
2171
- "rstrip": false,
2172
- "normalized": false,
2173
- "special": false
2174
- },
2175
- {
2176
- "id": 241,
2177
- "content": "<extra_id_236>",
2178
- "single_word": false,
2179
- "lstrip": false,
2180
- "rstrip": false,
2181
- "normalized": false,
2182
- "special": false
2183
- },
2184
- {
2185
- "id": 242,
2186
- "content": "<extra_id_237>",
2187
- "single_word": false,
2188
- "lstrip": false,
2189
- "rstrip": false,
2190
- "normalized": false,
2191
- "special": false
2192
- },
2193
- {
2194
- "id": 243,
2195
- "content": "<extra_id_238>",
2196
- "single_word": false,
2197
- "lstrip": false,
2198
- "rstrip": false,
2199
- "normalized": false,
2200
- "special": false
2201
- },
2202
- {
2203
- "id": 244,
2204
- "content": "<extra_id_239>",
2205
- "single_word": false,
2206
- "lstrip": false,
2207
- "rstrip": false,
2208
- "normalized": false,
2209
- "special": false
2210
- },
2211
- {
2212
- "id": 245,
2213
- "content": "<extra_id_240>",
2214
- "single_word": false,
2215
- "lstrip": false,
2216
- "rstrip": false,
2217
- "normalized": false,
2218
- "special": false
2219
- },
2220
- {
2221
- "id": 246,
2222
- "content": "<extra_id_241>",
2223
- "single_word": false,
2224
- "lstrip": false,
2225
- "rstrip": false,
2226
- "normalized": false,
2227
- "special": false
2228
- },
2229
- {
2230
- "id": 247,
2231
- "content": "<extra_id_242>",
2232
- "single_word": false,
2233
- "lstrip": false,
2234
- "rstrip": false,
2235
- "normalized": false,
2236
- "special": false
2237
- },
2238
- {
2239
- "id": 248,
2240
- "content": "<extra_id_243>",
2241
- "single_word": false,
2242
- "lstrip": false,
2243
- "rstrip": false,
2244
- "normalized": false,
2245
- "special": false
2246
- },
2247
- {
2248
- "id": 249,
2249
- "content": "<extra_id_244>",
2250
- "single_word": false,
2251
- "lstrip": false,
2252
- "rstrip": false,
2253
- "normalized": false,
2254
- "special": false
2255
- },
2256
- {
2257
- "id": 250,
2258
- "content": "<extra_id_245>",
2259
- "single_word": false,
2260
- "lstrip": false,
2261
- "rstrip": false,
2262
- "normalized": false,
2263
- "special": false
2264
- },
2265
- {
2266
- "id": 251,
2267
- "content": "<extra_id_246>",
2268
- "single_word": false,
2269
- "lstrip": false,
2270
- "rstrip": false,
2271
- "normalized": false,
2272
- "special": false
2273
- },
2274
- {
2275
- "id": 252,
2276
- "content": "<extra_id_247>",
2277
- "single_word": false,
2278
- "lstrip": false,
2279
- "rstrip": false,
2280
- "normalized": false,
2281
- "special": false
2282
- },
2283
- {
2284
- "id": 253,
2285
- "content": "<extra_id_248>",
2286
- "single_word": false,
2287
- "lstrip": false,
2288
- "rstrip": false,
2289
- "normalized": false,
2290
- "special": false
2291
- },
2292
- {
2293
- "id": 254,
2294
- "content": "<extra_id_249>",
2295
- "single_word": false,
2296
- "lstrip": false,
2297
- "rstrip": false,
2298
- "normalized": false,
2299
- "special": false
2300
- },
2301
- {
2302
- "id": 255,
2303
- "content": "<extra_id_250>",
2304
- "single_word": false,
2305
- "lstrip": false,
2306
- "rstrip": false,
2307
- "normalized": false,
2308
- "special": false
2309
- },
2310
- {
2311
- "id": 256,
2312
- "content": "<extra_id_251>",
2313
- "single_word": false,
2314
- "lstrip": false,
2315
- "rstrip": false,
2316
- "normalized": false,
2317
- "special": false
2318
- },
2319
- {
2320
- "id": 257,
2321
- "content": "<extra_id_252>",
2322
- "single_word": false,
2323
- "lstrip": false,
2324
- "rstrip": false,
2325
- "normalized": false,
2326
- "special": false
2327
- },
2328
- {
2329
- "id": 258,
2330
- "content": "<extra_id_253>",
2331
- "single_word": false,
2332
- "lstrip": false,
2333
- "rstrip": false,
2334
- "normalized": false,
2335
- "special": false
2336
- },
2337
- {
2338
- "id": 259,
2339
- "content": "<extra_id_254>",
2340
- "single_word": false,
2341
- "lstrip": false,
2342
- "rstrip": false,
2343
- "normalized": false,
2344
- "special": false
2345
- },
2346
- {
2347
- "id": 260,
2348
- "content": "<extra_id_255>",
2349
- "single_word": false,
2350
- "lstrip": false,
2351
- "rstrip": false,
2352
- "normalized": false,
2353
- "special": false
2354
  }
2355
  ],
2356
  "normalizer": {
@@ -2456,7 +152,6 @@
2456
  "end_of_word_suffix": null,
2457
  "fuse_unk": true,
2458
  "byte_fallback": true,
2459
- "ignore_merges": false,
2460
  "vocab": {
2461
  "<unk>": 0,
2462
  "<s>": 1,
 
47
  "rstrip": false,
48
  "normalized": false,
49
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
50
  }
51
  ],
52
  "normalizer": {
 
152
  "end_of_word_suffix": null,
153
  "fuse_unk": true,
154
  "byte_fallback": true,
 
155
  "vocab": {
156
  "<unk>": 0,
157
  "<s>": 1,
tokenizer_config.json CHANGED
@@ -42,2054 +42,6 @@
42
  "rstrip": false,
43
  "single_word": false,
44
  "special": true
45
- },
46
- "5": {
47
- "content": "<extra_id_0>",
48
- "lstrip": false,
49
- "normalized": false,
50
- "rstrip": false,
51
- "single_word": false,
52
- "special": false
53
- },
54
- "6": {
55
- "content": "<extra_id_1>",
56
- "lstrip": false,
57
- "normalized": false,
58
- "rstrip": false,
59
- "single_word": false,
60
- "special": false
61
- },
62
- "7": {
63
- "content": "<extra_id_2>",
64
- "lstrip": false,
65
- "normalized": false,
66
- "rstrip": false,
67
- "single_word": false,
68
- "special": false
69
- },
70
- "8": {
71
- "content": "<extra_id_3>",
72
- "lstrip": false,
73
- "normalized": false,
74
- "rstrip": false,
75
- "single_word": false,
76
- "special": false
77
- },
78
- "9": {
79
- "content": "<extra_id_4>",
80
- "lstrip": false,
81
- "normalized": false,
82
- "rstrip": false,
83
- "single_word": false,
84
- "special": false
85
- },
86
- "10": {
87
- "content": "<extra_id_5>",
88
- "lstrip": false,
89
- "normalized": false,
90
- "rstrip": false,
91
- "single_word": false,
92
- "special": false
93
- },
94
- "11": {
95
- "content": "<extra_id_6>",
96
- "lstrip": false,
97
- "normalized": false,
98
- "rstrip": false,
99
- "single_word": false,
100
- "special": false
101
- },
102
- "12": {
103
- "content": "<extra_id_7>",
104
- "lstrip": false,
105
- "normalized": false,
106
- "rstrip": false,
107
- "single_word": false,
108
- "special": false
109
- },
110
- "13": {
111
- "content": "<extra_id_8>",
112
- "lstrip": false,
113
- "normalized": false,
114
- "rstrip": false,
115
- "single_word": false,
116
- "special": false
117
- },
118
- "14": {
119
- "content": "<extra_id_9>",
120
- "lstrip": false,
121
- "normalized": false,
122
- "rstrip": false,
123
- "single_word": false,
124
- "special": false
125
- },
126
- "15": {
127
- "content": "<extra_id_10>",
128
- "lstrip": false,
129
- "normalized": false,
130
- "rstrip": false,
131
- "single_word": false,
132
- "special": false
133
- },
134
- "16": {
135
- "content": "<extra_id_11>",
136
- "lstrip": false,
137
- "normalized": false,
138
- "rstrip": false,
139
- "single_word": false,
140
- "special": false
141
- },
142
- "17": {
143
- "content": "<extra_id_12>",
144
- "lstrip": false,
145
- "normalized": false,
146
- "rstrip": false,
147
- "single_word": false,
148
- "special": false
149
- },
150
- "18": {
151
- "content": "<extra_id_13>",
152
- "lstrip": false,
153
- "normalized": false,
154
- "rstrip": false,
155
- "single_word": false,
156
- "special": false
157
- },
158
- "19": {
159
- "content": "<extra_id_14>",
160
- "lstrip": false,
161
- "normalized": false,
162
- "rstrip": false,
163
- "single_word": false,
164
- "special": false
165
- },
166
- "20": {
167
- "content": "<extra_id_15>",
168
- "lstrip": false,
169
- "normalized": false,
170
- "rstrip": false,
171
- "single_word": false,
172
- "special": false
173
- },
174
- "21": {
175
- "content": "<extra_id_16>",
176
- "lstrip": false,
177
- "normalized": false,
178
- "rstrip": false,
179
- "single_word": false,
180
- "special": false
181
- },
182
- "22": {
183
- "content": "<extra_id_17>",
184
- "lstrip": false,
185
- "normalized": false,
186
- "rstrip": false,
187
- "single_word": false,
188
- "special": false
189
- },
190
- "23": {
191
- "content": "<extra_id_18>",
192
- "lstrip": false,
193
- "normalized": false,
194
- "rstrip": false,
195
- "single_word": false,
196
- "special": false
197
- },
198
- "24": {
199
- "content": "<extra_id_19>",
200
- "lstrip": false,
201
- "normalized": false,
202
- "rstrip": false,
203
- "single_word": false,
204
- "special": false
205
- },
206
- "25": {
207
- "content": "<extra_id_20>",
208
- "lstrip": false,
209
- "normalized": false,
210
- "rstrip": false,
211
- "single_word": false,
212
- "special": false
213
- },
214
- "26": {
215
- "content": "<extra_id_21>",
216
- "lstrip": false,
217
- "normalized": false,
218
- "rstrip": false,
219
- "single_word": false,
220
- "special": false
221
- },
222
- "27": {
223
- "content": "<extra_id_22>",
224
- "lstrip": false,
225
- "normalized": false,
226
- "rstrip": false,
227
- "single_word": false,
228
- "special": false
229
- },
230
- "28": {
231
- "content": "<extra_id_23>",
232
- "lstrip": false,
233
- "normalized": false,
234
- "rstrip": false,
235
- "single_word": false,
236
- "special": false
237
- },
238
- "29": {
239
- "content": "<extra_id_24>",
240
- "lstrip": false,
241
- "normalized": false,
242
- "rstrip": false,
243
- "single_word": false,
244
- "special": false
245
- },
246
- "30": {
247
- "content": "<extra_id_25>",
248
- "lstrip": false,
249
- "normalized": false,
250
- "rstrip": false,
251
- "single_word": false,
252
- "special": false
253
- },
254
- "31": {
255
- "content": "<extra_id_26>",
256
- "lstrip": false,
257
- "normalized": false,
258
- "rstrip": false,
259
- "single_word": false,
260
- "special": false
261
- },
262
- "32": {
263
- "content": "<extra_id_27>",
264
- "lstrip": false,
265
- "normalized": false,
266
- "rstrip": false,
267
- "single_word": false,
268
- "special": false
269
- },
270
- "33": {
271
- "content": "<extra_id_28>",
272
- "lstrip": false,
273
- "normalized": false,
274
- "rstrip": false,
275
- "single_word": false,
276
- "special": false
277
- },
278
- "34": {
279
- "content": "<extra_id_29>",
280
- "lstrip": false,
281
- "normalized": false,
282
- "rstrip": false,
283
- "single_word": false,
284
- "special": false
285
- },
286
- "35": {
287
- "content": "<extra_id_30>",
288
- "lstrip": false,
289
- "normalized": false,
290
- "rstrip": false,
291
- "single_word": false,
292
- "special": false
293
- },
294
- "36": {
295
- "content": "<extra_id_31>",
296
- "lstrip": false,
297
- "normalized": false,
298
- "rstrip": false,
299
- "single_word": false,
300
- "special": false
301
- },
302
- "37": {
303
- "content": "<extra_id_32>",
304
- "lstrip": false,
305
- "normalized": false,
306
- "rstrip": false,
307
- "single_word": false,
308
- "special": false
309
- },
310
- "38": {
311
- "content": "<extra_id_33>",
312
- "lstrip": false,
313
- "normalized": false,
314
- "rstrip": false,
315
- "single_word": false,
316
- "special": false
317
- },
318
- "39": {
319
- "content": "<extra_id_34>",
320
- "lstrip": false,
321
- "normalized": false,
322
- "rstrip": false,
323
- "single_word": false,
324
- "special": false
325
- },
326
- "40": {
327
- "content": "<extra_id_35>",
328
- "lstrip": false,
329
- "normalized": false,
330
- "rstrip": false,
331
- "single_word": false,
332
- "special": false
333
- },
334
- "41": {
335
- "content": "<extra_id_36>",
336
- "lstrip": false,
337
- "normalized": false,
338
- "rstrip": false,
339
- "single_word": false,
340
- "special": false
341
- },
342
- "42": {
343
- "content": "<extra_id_37>",
344
- "lstrip": false,
345
- "normalized": false,
346
- "rstrip": false,
347
- "single_word": false,
348
- "special": false
349
- },
350
- "43": {
351
- "content": "<extra_id_38>",
352
- "lstrip": false,
353
- "normalized": false,
354
- "rstrip": false,
355
- "single_word": false,
356
- "special": false
357
- },
358
- "44": {
359
- "content": "<extra_id_39>",
360
- "lstrip": false,
361
- "normalized": false,
362
- "rstrip": false,
363
- "single_word": false,
364
- "special": false
365
- },
366
- "45": {
367
- "content": "<extra_id_40>",
368
- "lstrip": false,
369
- "normalized": false,
370
- "rstrip": false,
371
- "single_word": false,
372
- "special": false
373
- },
374
- "46": {
375
- "content": "<extra_id_41>",
376
- "lstrip": false,
377
- "normalized": false,
378
- "rstrip": false,
379
- "single_word": false,
380
- "special": false
381
- },
382
- "47": {
383
- "content": "<extra_id_42>",
384
- "lstrip": false,
385
- "normalized": false,
386
- "rstrip": false,
387
- "single_word": false,
388
- "special": false
389
- },
390
- "48": {
391
- "content": "<extra_id_43>",
392
- "lstrip": false,
393
- "normalized": false,
394
- "rstrip": false,
395
- "single_word": false,
396
- "special": false
397
- },
398
- "49": {
399
- "content": "<extra_id_44>",
400
- "lstrip": false,
401
- "normalized": false,
402
- "rstrip": false,
403
- "single_word": false,
404
- "special": false
405
- },
406
- "50": {
407
- "content": "<extra_id_45>",
408
- "lstrip": false,
409
- "normalized": false,
410
- "rstrip": false,
411
- "single_word": false,
412
- "special": false
413
- },
414
- "51": {
415
- "content": "<extra_id_46>",
416
- "lstrip": false,
417
- "normalized": false,
418
- "rstrip": false,
419
- "single_word": false,
420
- "special": false
421
- },
422
- "52": {
423
- "content": "<extra_id_47>",
424
- "lstrip": false,
425
- "normalized": false,
426
- "rstrip": false,
427
- "single_word": false,
428
- "special": false
429
- },
430
- "53": {
431
- "content": "<extra_id_48>",
432
- "lstrip": false,
433
- "normalized": false,
434
- "rstrip": false,
435
- "single_word": false,
436
- "special": false
437
- },
438
- "54": {
439
- "content": "<extra_id_49>",
440
- "lstrip": false,
441
- "normalized": false,
442
- "rstrip": false,
443
- "single_word": false,
444
- "special": false
445
- },
446
- "55": {
447
- "content": "<extra_id_50>",
448
- "lstrip": false,
449
- "normalized": false,
450
- "rstrip": false,
451
- "single_word": false,
452
- "special": false
453
- },
454
- "56": {
455
- "content": "<extra_id_51>",
456
- "lstrip": false,
457
- "normalized": false,
458
- "rstrip": false,
459
- "single_word": false,
460
- "special": false
461
- },
462
- "57": {
463
- "content": "<extra_id_52>",
464
- "lstrip": false,
465
- "normalized": false,
466
- "rstrip": false,
467
- "single_word": false,
468
- "special": false
469
- },
470
- "58": {
471
- "content": "<extra_id_53>",
472
- "lstrip": false,
473
- "normalized": false,
474
- "rstrip": false,
475
- "single_word": false,
476
- "special": false
477
- },
478
- "59": {
479
- "content": "<extra_id_54>",
480
- "lstrip": false,
481
- "normalized": false,
482
- "rstrip": false,
483
- "single_word": false,
484
- "special": false
485
- },
486
- "60": {
487
- "content": "<extra_id_55>",
488
- "lstrip": false,
489
- "normalized": false,
490
- "rstrip": false,
491
- "single_word": false,
492
- "special": false
493
- },
494
- "61": {
495
- "content": "<extra_id_56>",
496
- "lstrip": false,
497
- "normalized": false,
498
- "rstrip": false,
499
- "single_word": false,
500
- "special": false
501
- },
502
- "62": {
503
- "content": "<extra_id_57>",
504
- "lstrip": false,
505
- "normalized": false,
506
- "rstrip": false,
507
- "single_word": false,
508
- "special": false
509
- },
510
- "63": {
511
- "content": "<extra_id_58>",
512
- "lstrip": false,
513
- "normalized": false,
514
- "rstrip": false,
515
- "single_word": false,
516
- "special": false
517
- },
518
- "64": {
519
- "content": "<extra_id_59>",
520
- "lstrip": false,
521
- "normalized": false,
522
- "rstrip": false,
523
- "single_word": false,
524
- "special": false
525
- },
526
- "65": {
527
- "content": "<extra_id_60>",
528
- "lstrip": false,
529
- "normalized": false,
530
- "rstrip": false,
531
- "single_word": false,
532
- "special": false
533
- },
534
- "66": {
535
- "content": "<extra_id_61>",
536
- "lstrip": false,
537
- "normalized": false,
538
- "rstrip": false,
539
- "single_word": false,
540
- "special": false
541
- },
542
- "67": {
543
- "content": "<extra_id_62>",
544
- "lstrip": false,
545
- "normalized": false,
546
- "rstrip": false,
547
- "single_word": false,
548
- "special": false
549
- },
550
- "68": {
551
- "content": "<extra_id_63>",
552
- "lstrip": false,
553
- "normalized": false,
554
- "rstrip": false,
555
- "single_word": false,
556
- "special": false
557
- },
558
- "69": {
559
- "content": "<extra_id_64>",
560
- "lstrip": false,
561
- "normalized": false,
562
- "rstrip": false,
563
- "single_word": false,
564
- "special": false
565
- },
566
- "70": {
567
- "content": "<extra_id_65>",
568
- "lstrip": false,
569
- "normalized": false,
570
- "rstrip": false,
571
- "single_word": false,
572
- "special": false
573
- },
574
- "71": {
575
- "content": "<extra_id_66>",
576
- "lstrip": false,
577
- "normalized": false,
578
- "rstrip": false,
579
- "single_word": false,
580
- "special": false
581
- },
582
- "72": {
583
- "content": "<extra_id_67>",
584
- "lstrip": false,
585
- "normalized": false,
586
- "rstrip": false,
587
- "single_word": false,
588
- "special": false
589
- },
590
- "73": {
591
- "content": "<extra_id_68>",
592
- "lstrip": false,
593
- "normalized": false,
594
- "rstrip": false,
595
- "single_word": false,
596
- "special": false
597
- },
598
- "74": {
599
- "content": "<extra_id_69>",
600
- "lstrip": false,
601
- "normalized": false,
602
- "rstrip": false,
603
- "single_word": false,
604
- "special": false
605
- },
606
- "75": {
607
- "content": "<extra_id_70>",
608
- "lstrip": false,
609
- "normalized": false,
610
- "rstrip": false,
611
- "single_word": false,
612
- "special": false
613
- },
614
- "76": {
615
- "content": "<extra_id_71>",
616
- "lstrip": false,
617
- "normalized": false,
618
- "rstrip": false,
619
- "single_word": false,
620
- "special": false
621
- },
622
- "77": {
623
- "content": "<extra_id_72>",
624
- "lstrip": false,
625
- "normalized": false,
626
- "rstrip": false,
627
- "single_word": false,
628
- "special": false
629
- },
630
- "78": {
631
- "content": "<extra_id_73>",
632
- "lstrip": false,
633
- "normalized": false,
634
- "rstrip": false,
635
- "single_word": false,
636
- "special": false
637
- },
638
- "79": {
639
- "content": "<extra_id_74>",
640
- "lstrip": false,
641
- "normalized": false,
642
- "rstrip": false,
643
- "single_word": false,
644
- "special": false
645
- },
646
- "80": {
647
- "content": "<extra_id_75>",
648
- "lstrip": false,
649
- "normalized": false,
650
- "rstrip": false,
651
- "single_word": false,
652
- "special": false
653
- },
654
- "81": {
655
- "content": "<extra_id_76>",
656
- "lstrip": false,
657
- "normalized": false,
658
- "rstrip": false,
659
- "single_word": false,
660
- "special": false
661
- },
662
- "82": {
663
- "content": "<extra_id_77>",
664
- "lstrip": false,
665
- "normalized": false,
666
- "rstrip": false,
667
- "single_word": false,
668
- "special": false
669
- },
670
- "83": {
671
- "content": "<extra_id_78>",
672
- "lstrip": false,
673
- "normalized": false,
674
- "rstrip": false,
675
- "single_word": false,
676
- "special": false
677
- },
678
- "84": {
679
- "content": "<extra_id_79>",
680
- "lstrip": false,
681
- "normalized": false,
682
- "rstrip": false,
683
- "single_word": false,
684
- "special": false
685
- },
686
- "85": {
687
- "content": "<extra_id_80>",
688
- "lstrip": false,
689
- "normalized": false,
690
- "rstrip": false,
691
- "single_word": false,
692
- "special": false
693
- },
694
- "86": {
695
- "content": "<extra_id_81>",
696
- "lstrip": false,
697
- "normalized": false,
698
- "rstrip": false,
699
- "single_word": false,
700
- "special": false
701
- },
702
- "87": {
703
- "content": "<extra_id_82>",
704
- "lstrip": false,
705
- "normalized": false,
706
- "rstrip": false,
707
- "single_word": false,
708
- "special": false
709
- },
710
- "88": {
711
- "content": "<extra_id_83>",
712
- "lstrip": false,
713
- "normalized": false,
714
- "rstrip": false,
715
- "single_word": false,
716
- "special": false
717
- },
718
- "89": {
719
- "content": "<extra_id_84>",
720
- "lstrip": false,
721
- "normalized": false,
722
- "rstrip": false,
723
- "single_word": false,
724
- "special": false
725
- },
726
- "90": {
727
- "content": "<extra_id_85>",
728
- "lstrip": false,
729
- "normalized": false,
730
- "rstrip": false,
731
- "single_word": false,
732
- "special": false
733
- },
734
- "91": {
735
- "content": "<extra_id_86>",
736
- "lstrip": false,
737
- "normalized": false,
738
- "rstrip": false,
739
- "single_word": false,
740
- "special": false
741
- },
742
- "92": {
743
- "content": "<extra_id_87>",
744
- "lstrip": false,
745
- "normalized": false,
746
- "rstrip": false,
747
- "single_word": false,
748
- "special": false
749
- },
750
- "93": {
751
- "content": "<extra_id_88>",
752
- "lstrip": false,
753
- "normalized": false,
754
- "rstrip": false,
755
- "single_word": false,
756
- "special": false
757
- },
758
- "94": {
759
- "content": "<extra_id_89>",
760
- "lstrip": false,
761
- "normalized": false,
762
- "rstrip": false,
763
- "single_word": false,
764
- "special": false
765
- },
766
- "95": {
767
- "content": "<extra_id_90>",
768
- "lstrip": false,
769
- "normalized": false,
770
- "rstrip": false,
771
- "single_word": false,
772
- "special": false
773
- },
774
- "96": {
775
- "content": "<extra_id_91>",
776
- "lstrip": false,
777
- "normalized": false,
778
- "rstrip": false,
779
- "single_word": false,
780
- "special": false
781
- },
782
- "97": {
783
- "content": "<extra_id_92>",
784
- "lstrip": false,
785
- "normalized": false,
786
- "rstrip": false,
787
- "single_word": false,
788
- "special": false
789
- },
790
- "98": {
791
- "content": "<extra_id_93>",
792
- "lstrip": false,
793
- "normalized": false,
794
- "rstrip": false,
795
- "single_word": false,
796
- "special": false
797
- },
798
- "99": {
799
- "content": "<extra_id_94>",
800
- "lstrip": false,
801
- "normalized": false,
802
- "rstrip": false,
803
- "single_word": false,
804
- "special": false
805
- },
806
- "100": {
807
- "content": "<extra_id_95>",
808
- "lstrip": false,
809
- "normalized": false,
810
- "rstrip": false,
811
- "single_word": false,
812
- "special": false
813
- },
814
- "101": {
815
- "content": "<extra_id_96>",
816
- "lstrip": false,
817
- "normalized": false,
818
- "rstrip": false,
819
- "single_word": false,
820
- "special": false
821
- },
822
- "102": {
823
- "content": "<extra_id_97>",
824
- "lstrip": false,
825
- "normalized": false,
826
- "rstrip": false,
827
- "single_word": false,
828
- "special": false
829
- },
830
- "103": {
831
- "content": "<extra_id_98>",
832
- "lstrip": false,
833
- "normalized": false,
834
- "rstrip": false,
835
- "single_word": false,
836
- "special": false
837
- },
838
- "104": {
839
- "content": "<extra_id_99>",
840
- "lstrip": false,
841
- "normalized": false,
842
- "rstrip": false,
843
- "single_word": false,
844
- "special": false
845
- },
846
- "105": {
847
- "content": "<extra_id_100>",
848
- "lstrip": false,
849
- "normalized": false,
850
- "rstrip": false,
851
- "single_word": false,
852
- "special": false
853
- },
854
- "106": {
855
- "content": "<extra_id_101>",
856
- "lstrip": false,
857
- "normalized": false,
858
- "rstrip": false,
859
- "single_word": false,
860
- "special": false
861
- },
862
- "107": {
863
- "content": "<extra_id_102>",
864
- "lstrip": false,
865
- "normalized": false,
866
- "rstrip": false,
867
- "single_word": false,
868
- "special": false
869
- },
870
- "108": {
871
- "content": "<extra_id_103>",
872
- "lstrip": false,
873
- "normalized": false,
874
- "rstrip": false,
875
- "single_word": false,
876
- "special": false
877
- },
878
- "109": {
879
- "content": "<extra_id_104>",
880
- "lstrip": false,
881
- "normalized": false,
882
- "rstrip": false,
883
- "single_word": false,
884
- "special": false
885
- },
886
- "110": {
887
- "content": "<extra_id_105>",
888
- "lstrip": false,
889
- "normalized": false,
890
- "rstrip": false,
891
- "single_word": false,
892
- "special": false
893
- },
894
- "111": {
895
- "content": "<extra_id_106>",
896
- "lstrip": false,
897
- "normalized": false,
898
- "rstrip": false,
899
- "single_word": false,
900
- "special": false
901
- },
902
- "112": {
903
- "content": "<extra_id_107>",
904
- "lstrip": false,
905
- "normalized": false,
906
- "rstrip": false,
907
- "single_word": false,
908
- "special": false
909
- },
910
- "113": {
911
- "content": "<extra_id_108>",
912
- "lstrip": false,
913
- "normalized": false,
914
- "rstrip": false,
915
- "single_word": false,
916
- "special": false
917
- },
918
- "114": {
919
- "content": "<extra_id_109>",
920
- "lstrip": false,
921
- "normalized": false,
922
- "rstrip": false,
923
- "single_word": false,
924
- "special": false
925
- },
926
- "115": {
927
- "content": "<extra_id_110>",
928
- "lstrip": false,
929
- "normalized": false,
930
- "rstrip": false,
931
- "single_word": false,
932
- "special": false
933
- },
934
- "116": {
935
- "content": "<extra_id_111>",
936
- "lstrip": false,
937
- "normalized": false,
938
- "rstrip": false,
939
- "single_word": false,
940
- "special": false
941
- },
942
- "117": {
943
- "content": "<extra_id_112>",
944
- "lstrip": false,
945
- "normalized": false,
946
- "rstrip": false,
947
- "single_word": false,
948
- "special": false
949
- },
950
- "118": {
951
- "content": "<extra_id_113>",
952
- "lstrip": false,
953
- "normalized": false,
954
- "rstrip": false,
955
- "single_word": false,
956
- "special": false
957
- },
958
- "119": {
959
- "content": "<extra_id_114>",
960
- "lstrip": false,
961
- "normalized": false,
962
- "rstrip": false,
963
- "single_word": false,
964
- "special": false
965
- },
966
- "120": {
967
- "content": "<extra_id_115>",
968
- "lstrip": false,
969
- "normalized": false,
970
- "rstrip": false,
971
- "single_word": false,
972
- "special": false
973
- },
974
- "121": {
975
- "content": "<extra_id_116>",
976
- "lstrip": false,
977
- "normalized": false,
978
- "rstrip": false,
979
- "single_word": false,
980
- "special": false
981
- },
982
- "122": {
983
- "content": "<extra_id_117>",
984
- "lstrip": false,
985
- "normalized": false,
986
- "rstrip": false,
987
- "single_word": false,
988
- "special": false
989
- },
990
- "123": {
991
- "content": "<extra_id_118>",
992
- "lstrip": false,
993
- "normalized": false,
994
- "rstrip": false,
995
- "single_word": false,
996
- "special": false
997
- },
998
- "124": {
999
- "content": "<extra_id_119>",
1000
- "lstrip": false,
1001
- "normalized": false,
1002
- "rstrip": false,
1003
- "single_word": false,
1004
- "special": false
1005
- },
1006
- "125": {
1007
- "content": "<extra_id_120>",
1008
- "lstrip": false,
1009
- "normalized": false,
1010
- "rstrip": false,
1011
- "single_word": false,
1012
- "special": false
1013
- },
1014
- "126": {
1015
- "content": "<extra_id_121>",
1016
- "lstrip": false,
1017
- "normalized": false,
1018
- "rstrip": false,
1019
- "single_word": false,
1020
- "special": false
1021
- },
1022
- "127": {
1023
- "content": "<extra_id_122>",
1024
- "lstrip": false,
1025
- "normalized": false,
1026
- "rstrip": false,
1027
- "single_word": false,
1028
- "special": false
1029
- },
1030
- "128": {
1031
- "content": "<extra_id_123>",
1032
- "lstrip": false,
1033
- "normalized": false,
1034
- "rstrip": false,
1035
- "single_word": false,
1036
- "special": false
1037
- },
1038
- "129": {
1039
- "content": "<extra_id_124>",
1040
- "lstrip": false,
1041
- "normalized": false,
1042
- "rstrip": false,
1043
- "single_word": false,
1044
- "special": false
1045
- },
1046
- "130": {
1047
- "content": "<extra_id_125>",
1048
- "lstrip": false,
1049
- "normalized": false,
1050
- "rstrip": false,
1051
- "single_word": false,
1052
- "special": false
1053
- },
1054
- "131": {
1055
- "content": "<extra_id_126>",
1056
- "lstrip": false,
1057
- "normalized": false,
1058
- "rstrip": false,
1059
- "single_word": false,
1060
- "special": false
1061
- },
1062
- "132": {
1063
- "content": "<extra_id_127>",
1064
- "lstrip": false,
1065
- "normalized": false,
1066
- "rstrip": false,
1067
- "single_word": false,
1068
- "special": false
1069
- },
1070
- "133": {
1071
- "content": "<extra_id_128>",
1072
- "lstrip": false,
1073
- "normalized": false,
1074
- "rstrip": false,
1075
- "single_word": false,
1076
- "special": false
1077
- },
1078
- "134": {
1079
- "content": "<extra_id_129>",
1080
- "lstrip": false,
1081
- "normalized": false,
1082
- "rstrip": false,
1083
- "single_word": false,
1084
- "special": false
1085
- },
1086
- "135": {
1087
- "content": "<extra_id_130>",
1088
- "lstrip": false,
1089
- "normalized": false,
1090
- "rstrip": false,
1091
- "single_word": false,
1092
- "special": false
1093
- },
1094
- "136": {
1095
- "content": "<extra_id_131>",
1096
- "lstrip": false,
1097
- "normalized": false,
1098
- "rstrip": false,
1099
- "single_word": false,
1100
- "special": false
1101
- },
1102
- "137": {
1103
- "content": "<extra_id_132>",
1104
- "lstrip": false,
1105
- "normalized": false,
1106
- "rstrip": false,
1107
- "single_word": false,
1108
- "special": false
1109
- },
1110
- "138": {
1111
- "content": "<extra_id_133>",
1112
- "lstrip": false,
1113
- "normalized": false,
1114
- "rstrip": false,
1115
- "single_word": false,
1116
- "special": false
1117
- },
1118
- "139": {
1119
- "content": "<extra_id_134>",
1120
- "lstrip": false,
1121
- "normalized": false,
1122
- "rstrip": false,
1123
- "single_word": false,
1124
- "special": false
1125
- },
1126
- "140": {
1127
- "content": "<extra_id_135>",
1128
- "lstrip": false,
1129
- "normalized": false,
1130
- "rstrip": false,
1131
- "single_word": false,
1132
- "special": false
1133
- },
1134
- "141": {
1135
- "content": "<extra_id_136>",
1136
- "lstrip": false,
1137
- "normalized": false,
1138
- "rstrip": false,
1139
- "single_word": false,
1140
- "special": false
1141
- },
1142
- "142": {
1143
- "content": "<extra_id_137>",
1144
- "lstrip": false,
1145
- "normalized": false,
1146
- "rstrip": false,
1147
- "single_word": false,
1148
- "special": false
1149
- },
1150
- "143": {
1151
- "content": "<extra_id_138>",
1152
- "lstrip": false,
1153
- "normalized": false,
1154
- "rstrip": false,
1155
- "single_word": false,
1156
- "special": false
1157
- },
1158
- "144": {
1159
- "content": "<extra_id_139>",
1160
- "lstrip": false,
1161
- "normalized": false,
1162
- "rstrip": false,
1163
- "single_word": false,
1164
- "special": false
1165
- },
1166
- "145": {
1167
- "content": "<extra_id_140>",
1168
- "lstrip": false,
1169
- "normalized": false,
1170
- "rstrip": false,
1171
- "single_word": false,
1172
- "special": false
1173
- },
1174
- "146": {
1175
- "content": "<extra_id_141>",
1176
- "lstrip": false,
1177
- "normalized": false,
1178
- "rstrip": false,
1179
- "single_word": false,
1180
- "special": false
1181
- },
1182
- "147": {
1183
- "content": "<extra_id_142>",
1184
- "lstrip": false,
1185
- "normalized": false,
1186
- "rstrip": false,
1187
- "single_word": false,
1188
- "special": false
1189
- },
1190
- "148": {
1191
- "content": "<extra_id_143>",
1192
- "lstrip": false,
1193
- "normalized": false,
1194
- "rstrip": false,
1195
- "single_word": false,
1196
- "special": false
1197
- },
1198
- "149": {
1199
- "content": "<extra_id_144>",
1200
- "lstrip": false,
1201
- "normalized": false,
1202
- "rstrip": false,
1203
- "single_word": false,
1204
- "special": false
1205
- },
1206
- "150": {
1207
- "content": "<extra_id_145>",
1208
- "lstrip": false,
1209
- "normalized": false,
1210
- "rstrip": false,
1211
- "single_word": false,
1212
- "special": false
1213
- },
1214
- "151": {
1215
- "content": "<extra_id_146>",
1216
- "lstrip": false,
1217
- "normalized": false,
1218
- "rstrip": false,
1219
- "single_word": false,
1220
- "special": false
1221
- },
1222
- "152": {
1223
- "content": "<extra_id_147>",
1224
- "lstrip": false,
1225
- "normalized": false,
1226
- "rstrip": false,
1227
- "single_word": false,
1228
- "special": false
1229
- },
1230
- "153": {
1231
- "content": "<extra_id_148>",
1232
- "lstrip": false,
1233
- "normalized": false,
1234
- "rstrip": false,
1235
- "single_word": false,
1236
- "special": false
1237
- },
1238
- "154": {
1239
- "content": "<extra_id_149>",
1240
- "lstrip": false,
1241
- "normalized": false,
1242
- "rstrip": false,
1243
- "single_word": false,
1244
- "special": false
1245
- },
1246
- "155": {
1247
- "content": "<extra_id_150>",
1248
- "lstrip": false,
1249
- "normalized": false,
1250
- "rstrip": false,
1251
- "single_word": false,
1252
- "special": false
1253
- },
1254
- "156": {
1255
- "content": "<extra_id_151>",
1256
- "lstrip": false,
1257
- "normalized": false,
1258
- "rstrip": false,
1259
- "single_word": false,
1260
- "special": false
1261
- },
1262
- "157": {
1263
- "content": "<extra_id_152>",
1264
- "lstrip": false,
1265
- "normalized": false,
1266
- "rstrip": false,
1267
- "single_word": false,
1268
- "special": false
1269
- },
1270
- "158": {
1271
- "content": "<extra_id_153>",
1272
- "lstrip": false,
1273
- "normalized": false,
1274
- "rstrip": false,
1275
- "single_word": false,
1276
- "special": false
1277
- },
1278
- "159": {
1279
- "content": "<extra_id_154>",
1280
- "lstrip": false,
1281
- "normalized": false,
1282
- "rstrip": false,
1283
- "single_word": false,
1284
- "special": false
1285
- },
1286
- "160": {
1287
- "content": "<extra_id_155>",
1288
- "lstrip": false,
1289
- "normalized": false,
1290
- "rstrip": false,
1291
- "single_word": false,
1292
- "special": false
1293
- },
1294
- "161": {
1295
- "content": "<extra_id_156>",
1296
- "lstrip": false,
1297
- "normalized": false,
1298
- "rstrip": false,
1299
- "single_word": false,
1300
- "special": false
1301
- },
1302
- "162": {
1303
- "content": "<extra_id_157>",
1304
- "lstrip": false,
1305
- "normalized": false,
1306
- "rstrip": false,
1307
- "single_word": false,
1308
- "special": false
1309
- },
1310
- "163": {
1311
- "content": "<extra_id_158>",
1312
- "lstrip": false,
1313
- "normalized": false,
1314
- "rstrip": false,
1315
- "single_word": false,
1316
- "special": false
1317
- },
1318
- "164": {
1319
- "content": "<extra_id_159>",
1320
- "lstrip": false,
1321
- "normalized": false,
1322
- "rstrip": false,
1323
- "single_word": false,
1324
- "special": false
1325
- },
1326
- "165": {
1327
- "content": "<extra_id_160>",
1328
- "lstrip": false,
1329
- "normalized": false,
1330
- "rstrip": false,
1331
- "single_word": false,
1332
- "special": false
1333
- },
1334
- "166": {
1335
- "content": "<extra_id_161>",
1336
- "lstrip": false,
1337
- "normalized": false,
1338
- "rstrip": false,
1339
- "single_word": false,
1340
- "special": false
1341
- },
1342
- "167": {
1343
- "content": "<extra_id_162>",
1344
- "lstrip": false,
1345
- "normalized": false,
1346
- "rstrip": false,
1347
- "single_word": false,
1348
- "special": false
1349
- },
1350
- "168": {
1351
- "content": "<extra_id_163>",
1352
- "lstrip": false,
1353
- "normalized": false,
1354
- "rstrip": false,
1355
- "single_word": false,
1356
- "special": false
1357
- },
1358
- "169": {
1359
- "content": "<extra_id_164>",
1360
- "lstrip": false,
1361
- "normalized": false,
1362
- "rstrip": false,
1363
- "single_word": false,
1364
- "special": false
1365
- },
1366
- "170": {
1367
- "content": "<extra_id_165>",
1368
- "lstrip": false,
1369
- "normalized": false,
1370
- "rstrip": false,
1371
- "single_word": false,
1372
- "special": false
1373
- },
1374
- "171": {
1375
- "content": "<extra_id_166>",
1376
- "lstrip": false,
1377
- "normalized": false,
1378
- "rstrip": false,
1379
- "single_word": false,
1380
- "special": false
1381
- },
1382
- "172": {
1383
- "content": "<extra_id_167>",
1384
- "lstrip": false,
1385
- "normalized": false,
1386
- "rstrip": false,
1387
- "single_word": false,
1388
- "special": false
1389
- },
1390
- "173": {
1391
- "content": "<extra_id_168>",
1392
- "lstrip": false,
1393
- "normalized": false,
1394
- "rstrip": false,
1395
- "single_word": false,
1396
- "special": false
1397
- },
1398
- "174": {
1399
- "content": "<extra_id_169>",
1400
- "lstrip": false,
1401
- "normalized": false,
1402
- "rstrip": false,
1403
- "single_word": false,
1404
- "special": false
1405
- },
1406
- "175": {
1407
- "content": "<extra_id_170>",
1408
- "lstrip": false,
1409
- "normalized": false,
1410
- "rstrip": false,
1411
- "single_word": false,
1412
- "special": false
1413
- },
1414
- "176": {
1415
- "content": "<extra_id_171>",
1416
- "lstrip": false,
1417
- "normalized": false,
1418
- "rstrip": false,
1419
- "single_word": false,
1420
- "special": false
1421
- },
1422
- "177": {
1423
- "content": "<extra_id_172>",
1424
- "lstrip": false,
1425
- "normalized": false,
1426
- "rstrip": false,
1427
- "single_word": false,
1428
- "special": false
1429
- },
1430
- "178": {
1431
- "content": "<extra_id_173>",
1432
- "lstrip": false,
1433
- "normalized": false,
1434
- "rstrip": false,
1435
- "single_word": false,
1436
- "special": false
1437
- },
1438
- "179": {
1439
- "content": "<extra_id_174>",
1440
- "lstrip": false,
1441
- "normalized": false,
1442
- "rstrip": false,
1443
- "single_word": false,
1444
- "special": false
1445
- },
1446
- "180": {
1447
- "content": "<extra_id_175>",
1448
- "lstrip": false,
1449
- "normalized": false,
1450
- "rstrip": false,
1451
- "single_word": false,
1452
- "special": false
1453
- },
1454
- "181": {
1455
- "content": "<extra_id_176>",
1456
- "lstrip": false,
1457
- "normalized": false,
1458
- "rstrip": false,
1459
- "single_word": false,
1460
- "special": false
1461
- },
1462
- "182": {
1463
- "content": "<extra_id_177>",
1464
- "lstrip": false,
1465
- "normalized": false,
1466
- "rstrip": false,
1467
- "single_word": false,
1468
- "special": false
1469
- },
1470
- "183": {
1471
- "content": "<extra_id_178>",
1472
- "lstrip": false,
1473
- "normalized": false,
1474
- "rstrip": false,
1475
- "single_word": false,
1476
- "special": false
1477
- },
1478
- "184": {
1479
- "content": "<extra_id_179>",
1480
- "lstrip": false,
1481
- "normalized": false,
1482
- "rstrip": false,
1483
- "single_word": false,
1484
- "special": false
1485
- },
1486
- "185": {
1487
- "content": "<extra_id_180>",
1488
- "lstrip": false,
1489
- "normalized": false,
1490
- "rstrip": false,
1491
- "single_word": false,
1492
- "special": false
1493
- },
1494
- "186": {
1495
- "content": "<extra_id_181>",
1496
- "lstrip": false,
1497
- "normalized": false,
1498
- "rstrip": false,
1499
- "single_word": false,
1500
- "special": false
1501
- },
1502
- "187": {
1503
- "content": "<extra_id_182>",
1504
- "lstrip": false,
1505
- "normalized": false,
1506
- "rstrip": false,
1507
- "single_word": false,
1508
- "special": false
1509
- },
1510
- "188": {
1511
- "content": "<extra_id_183>",
1512
- "lstrip": false,
1513
- "normalized": false,
1514
- "rstrip": false,
1515
- "single_word": false,
1516
- "special": false
1517
- },
1518
- "189": {
1519
- "content": "<extra_id_184>",
1520
- "lstrip": false,
1521
- "normalized": false,
1522
- "rstrip": false,
1523
- "single_word": false,
1524
- "special": false
1525
- },
1526
- "190": {
1527
- "content": "<extra_id_185>",
1528
- "lstrip": false,
1529
- "normalized": false,
1530
- "rstrip": false,
1531
- "single_word": false,
1532
- "special": false
1533
- },
1534
- "191": {
1535
- "content": "<extra_id_186>",
1536
- "lstrip": false,
1537
- "normalized": false,
1538
- "rstrip": false,
1539
- "single_word": false,
1540
- "special": false
1541
- },
1542
- "192": {
1543
- "content": "<extra_id_187>",
1544
- "lstrip": false,
1545
- "normalized": false,
1546
- "rstrip": false,
1547
- "single_word": false,
1548
- "special": false
1549
- },
1550
- "193": {
1551
- "content": "<extra_id_188>",
1552
- "lstrip": false,
1553
- "normalized": false,
1554
- "rstrip": false,
1555
- "single_word": false,
1556
- "special": false
1557
- },
1558
- "194": {
1559
- "content": "<extra_id_189>",
1560
- "lstrip": false,
1561
- "normalized": false,
1562
- "rstrip": false,
1563
- "single_word": false,
1564
- "special": false
1565
- },
1566
- "195": {
1567
- "content": "<extra_id_190>",
1568
- "lstrip": false,
1569
- "normalized": false,
1570
- "rstrip": false,
1571
- "single_word": false,
1572
- "special": false
1573
- },
1574
- "196": {
1575
- "content": "<extra_id_191>",
1576
- "lstrip": false,
1577
- "normalized": false,
1578
- "rstrip": false,
1579
- "single_word": false,
1580
- "special": false
1581
- },
1582
- "197": {
1583
- "content": "<extra_id_192>",
1584
- "lstrip": false,
1585
- "normalized": false,
1586
- "rstrip": false,
1587
- "single_word": false,
1588
- "special": false
1589
- },
1590
- "198": {
1591
- "content": "<extra_id_193>",
1592
- "lstrip": false,
1593
- "normalized": false,
1594
- "rstrip": false,
1595
- "single_word": false,
1596
- "special": false
1597
- },
1598
- "199": {
1599
- "content": "<extra_id_194>",
1600
- "lstrip": false,
1601
- "normalized": false,
1602
- "rstrip": false,
1603
- "single_word": false,
1604
- "special": false
1605
- },
1606
- "200": {
1607
- "content": "<extra_id_195>",
1608
- "lstrip": false,
1609
- "normalized": false,
1610
- "rstrip": false,
1611
- "single_word": false,
1612
- "special": false
1613
- },
1614
- "201": {
1615
- "content": "<extra_id_196>",
1616
- "lstrip": false,
1617
- "normalized": false,
1618
- "rstrip": false,
1619
- "single_word": false,
1620
- "special": false
1621
- },
1622
- "202": {
1623
- "content": "<extra_id_197>",
1624
- "lstrip": false,
1625
- "normalized": false,
1626
- "rstrip": false,
1627
- "single_word": false,
1628
- "special": false
1629
- },
1630
- "203": {
1631
- "content": "<extra_id_198>",
1632
- "lstrip": false,
1633
- "normalized": false,
1634
- "rstrip": false,
1635
- "single_word": false,
1636
- "special": false
1637
- },
1638
- "204": {
1639
- "content": "<extra_id_199>",
1640
- "lstrip": false,
1641
- "normalized": false,
1642
- "rstrip": false,
1643
- "single_word": false,
1644
- "special": false
1645
- },
1646
- "205": {
1647
- "content": "<extra_id_200>",
1648
- "lstrip": false,
1649
- "normalized": false,
1650
- "rstrip": false,
1651
- "single_word": false,
1652
- "special": false
1653
- },
1654
- "206": {
1655
- "content": "<extra_id_201>",
1656
- "lstrip": false,
1657
- "normalized": false,
1658
- "rstrip": false,
1659
- "single_word": false,
1660
- "special": false
1661
- },
1662
- "207": {
1663
- "content": "<extra_id_202>",
1664
- "lstrip": false,
1665
- "normalized": false,
1666
- "rstrip": false,
1667
- "single_word": false,
1668
- "special": false
1669
- },
1670
- "208": {
1671
- "content": "<extra_id_203>",
1672
- "lstrip": false,
1673
- "normalized": false,
1674
- "rstrip": false,
1675
- "single_word": false,
1676
- "special": false
1677
- },
1678
- "209": {
1679
- "content": "<extra_id_204>",
1680
- "lstrip": false,
1681
- "normalized": false,
1682
- "rstrip": false,
1683
- "single_word": false,
1684
- "special": false
1685
- },
1686
- "210": {
1687
- "content": "<extra_id_205>",
1688
- "lstrip": false,
1689
- "normalized": false,
1690
- "rstrip": false,
1691
- "single_word": false,
1692
- "special": false
1693
- },
1694
- "211": {
1695
- "content": "<extra_id_206>",
1696
- "lstrip": false,
1697
- "normalized": false,
1698
- "rstrip": false,
1699
- "single_word": false,
1700
- "special": false
1701
- },
1702
- "212": {
1703
- "content": "<extra_id_207>",
1704
- "lstrip": false,
1705
- "normalized": false,
1706
- "rstrip": false,
1707
- "single_word": false,
1708
- "special": false
1709
- },
1710
- "213": {
1711
- "content": "<extra_id_208>",
1712
- "lstrip": false,
1713
- "normalized": false,
1714
- "rstrip": false,
1715
- "single_word": false,
1716
- "special": false
1717
- },
1718
- "214": {
1719
- "content": "<extra_id_209>",
1720
- "lstrip": false,
1721
- "normalized": false,
1722
- "rstrip": false,
1723
- "single_word": false,
1724
- "special": false
1725
- },
1726
- "215": {
1727
- "content": "<extra_id_210>",
1728
- "lstrip": false,
1729
- "normalized": false,
1730
- "rstrip": false,
1731
- "single_word": false,
1732
- "special": false
1733
- },
1734
- "216": {
1735
- "content": "<extra_id_211>",
1736
- "lstrip": false,
1737
- "normalized": false,
1738
- "rstrip": false,
1739
- "single_word": false,
1740
- "special": false
1741
- },
1742
- "217": {
1743
- "content": "<extra_id_212>",
1744
- "lstrip": false,
1745
- "normalized": false,
1746
- "rstrip": false,
1747
- "single_word": false,
1748
- "special": false
1749
- },
1750
- "218": {
1751
- "content": "<extra_id_213>",
1752
- "lstrip": false,
1753
- "normalized": false,
1754
- "rstrip": false,
1755
- "single_word": false,
1756
- "special": false
1757
- },
1758
- "219": {
1759
- "content": "<extra_id_214>",
1760
- "lstrip": false,
1761
- "normalized": false,
1762
- "rstrip": false,
1763
- "single_word": false,
1764
- "special": false
1765
- },
1766
- "220": {
1767
- "content": "<extra_id_215>",
1768
- "lstrip": false,
1769
- "normalized": false,
1770
- "rstrip": false,
1771
- "single_word": false,
1772
- "special": false
1773
- },
1774
- "221": {
1775
- "content": "<extra_id_216>",
1776
- "lstrip": false,
1777
- "normalized": false,
1778
- "rstrip": false,
1779
- "single_word": false,
1780
- "special": false
1781
- },
1782
- "222": {
1783
- "content": "<extra_id_217>",
1784
- "lstrip": false,
1785
- "normalized": false,
1786
- "rstrip": false,
1787
- "single_word": false,
1788
- "special": false
1789
- },
1790
- "223": {
1791
- "content": "<extra_id_218>",
1792
- "lstrip": false,
1793
- "normalized": false,
1794
- "rstrip": false,
1795
- "single_word": false,
1796
- "special": false
1797
- },
1798
- "224": {
1799
- "content": "<extra_id_219>",
1800
- "lstrip": false,
1801
- "normalized": false,
1802
- "rstrip": false,
1803
- "single_word": false,
1804
- "special": false
1805
- },
1806
- "225": {
1807
- "content": "<extra_id_220>",
1808
- "lstrip": false,
1809
- "normalized": false,
1810
- "rstrip": false,
1811
- "single_word": false,
1812
- "special": false
1813
- },
1814
- "226": {
1815
- "content": "<extra_id_221>",
1816
- "lstrip": false,
1817
- "normalized": false,
1818
- "rstrip": false,
1819
- "single_word": false,
1820
- "special": false
1821
- },
1822
- "227": {
1823
- "content": "<extra_id_222>",
1824
- "lstrip": false,
1825
- "normalized": false,
1826
- "rstrip": false,
1827
- "single_word": false,
1828
- "special": false
1829
- },
1830
- "228": {
1831
- "content": "<extra_id_223>",
1832
- "lstrip": false,
1833
- "normalized": false,
1834
- "rstrip": false,
1835
- "single_word": false,
1836
- "special": false
1837
- },
1838
- "229": {
1839
- "content": "<extra_id_224>",
1840
- "lstrip": false,
1841
- "normalized": false,
1842
- "rstrip": false,
1843
- "single_word": false,
1844
- "special": false
1845
- },
1846
- "230": {
1847
- "content": "<extra_id_225>",
1848
- "lstrip": false,
1849
- "normalized": false,
1850
- "rstrip": false,
1851
- "single_word": false,
1852
- "special": false
1853
- },
1854
- "231": {
1855
- "content": "<extra_id_226>",
1856
- "lstrip": false,
1857
- "normalized": false,
1858
- "rstrip": false,
1859
- "single_word": false,
1860
- "special": false
1861
- },
1862
- "232": {
1863
- "content": "<extra_id_227>",
1864
- "lstrip": false,
1865
- "normalized": false,
1866
- "rstrip": false,
1867
- "single_word": false,
1868
- "special": false
1869
- },
1870
- "233": {
1871
- "content": "<extra_id_228>",
1872
- "lstrip": false,
1873
- "normalized": false,
1874
- "rstrip": false,
1875
- "single_word": false,
1876
- "special": false
1877
- },
1878
- "234": {
1879
- "content": "<extra_id_229>",
1880
- "lstrip": false,
1881
- "normalized": false,
1882
- "rstrip": false,
1883
- "single_word": false,
1884
- "special": false
1885
- },
1886
- "235": {
1887
- "content": "<extra_id_230>",
1888
- "lstrip": false,
1889
- "normalized": false,
1890
- "rstrip": false,
1891
- "single_word": false,
1892
- "special": false
1893
- },
1894
- "236": {
1895
- "content": "<extra_id_231>",
1896
- "lstrip": false,
1897
- "normalized": false,
1898
- "rstrip": false,
1899
- "single_word": false,
1900
- "special": false
1901
- },
1902
- "237": {
1903
- "content": "<extra_id_232>",
1904
- "lstrip": false,
1905
- "normalized": false,
1906
- "rstrip": false,
1907
- "single_word": false,
1908
- "special": false
1909
- },
1910
- "238": {
1911
- "content": "<extra_id_233>",
1912
- "lstrip": false,
1913
- "normalized": false,
1914
- "rstrip": false,
1915
- "single_word": false,
1916
- "special": false
1917
- },
1918
- "239": {
1919
- "content": "<extra_id_234>",
1920
- "lstrip": false,
1921
- "normalized": false,
1922
- "rstrip": false,
1923
- "single_word": false,
1924
- "special": false
1925
- },
1926
- "240": {
1927
- "content": "<extra_id_235>",
1928
- "lstrip": false,
1929
- "normalized": false,
1930
- "rstrip": false,
1931
- "single_word": false,
1932
- "special": false
1933
- },
1934
- "241": {
1935
- "content": "<extra_id_236>",
1936
- "lstrip": false,
1937
- "normalized": false,
1938
- "rstrip": false,
1939
- "single_word": false,
1940
- "special": false
1941
- },
1942
- "242": {
1943
- "content": "<extra_id_237>",
1944
- "lstrip": false,
1945
- "normalized": false,
1946
- "rstrip": false,
1947
- "single_word": false,
1948
- "special": false
1949
- },
1950
- "243": {
1951
- "content": "<extra_id_238>",
1952
- "lstrip": false,
1953
- "normalized": false,
1954
- "rstrip": false,
1955
- "single_word": false,
1956
- "special": false
1957
- },
1958
- "244": {
1959
- "content": "<extra_id_239>",
1960
- "lstrip": false,
1961
- "normalized": false,
1962
- "rstrip": false,
1963
- "single_word": false,
1964
- "special": false
1965
- },
1966
- "245": {
1967
- "content": "<extra_id_240>",
1968
- "lstrip": false,
1969
- "normalized": false,
1970
- "rstrip": false,
1971
- "single_word": false,
1972
- "special": false
1973
- },
1974
- "246": {
1975
- "content": "<extra_id_241>",
1976
- "lstrip": false,
1977
- "normalized": false,
1978
- "rstrip": false,
1979
- "single_word": false,
1980
- "special": false
1981
- },
1982
- "247": {
1983
- "content": "<extra_id_242>",
1984
- "lstrip": false,
1985
- "normalized": false,
1986
- "rstrip": false,
1987
- "single_word": false,
1988
- "special": false
1989
- },
1990
- "248": {
1991
- "content": "<extra_id_243>",
1992
- "lstrip": false,
1993
- "normalized": false,
1994
- "rstrip": false,
1995
- "single_word": false,
1996
- "special": false
1997
- },
1998
- "249": {
1999
- "content": "<extra_id_244>",
2000
- "lstrip": false,
2001
- "normalized": false,
2002
- "rstrip": false,
2003
- "single_word": false,
2004
- "special": false
2005
- },
2006
- "250": {
2007
- "content": "<extra_id_245>",
2008
- "lstrip": false,
2009
- "normalized": false,
2010
- "rstrip": false,
2011
- "single_word": false,
2012
- "special": false
2013
- },
2014
- "251": {
2015
- "content": "<extra_id_246>",
2016
- "lstrip": false,
2017
- "normalized": false,
2018
- "rstrip": false,
2019
- "single_word": false,
2020
- "special": false
2021
- },
2022
- "252": {
2023
- "content": "<extra_id_247>",
2024
- "lstrip": false,
2025
- "normalized": false,
2026
- "rstrip": false,
2027
- "single_word": false,
2028
- "special": false
2029
- },
2030
- "253": {
2031
- "content": "<extra_id_248>",
2032
- "lstrip": false,
2033
- "normalized": false,
2034
- "rstrip": false,
2035
- "single_word": false,
2036
- "special": false
2037
- },
2038
- "254": {
2039
- "content": "<extra_id_249>",
2040
- "lstrip": false,
2041
- "normalized": false,
2042
- "rstrip": false,
2043
- "single_word": false,
2044
- "special": false
2045
- },
2046
- "255": {
2047
- "content": "<extra_id_250>",
2048
- "lstrip": false,
2049
- "normalized": false,
2050
- "rstrip": false,
2051
- "single_word": false,
2052
- "special": false
2053
- },
2054
- "256": {
2055
- "content": "<extra_id_251>",
2056
- "lstrip": false,
2057
- "normalized": false,
2058
- "rstrip": false,
2059
- "single_word": false,
2060
- "special": false
2061
- },
2062
- "257": {
2063
- "content": "<extra_id_252>",
2064
- "lstrip": false,
2065
- "normalized": false,
2066
- "rstrip": false,
2067
- "single_word": false,
2068
- "special": false
2069
- },
2070
- "258": {
2071
- "content": "<extra_id_253>",
2072
- "lstrip": false,
2073
- "normalized": false,
2074
- "rstrip": false,
2075
- "single_word": false,
2076
- "special": false
2077
- },
2078
- "259": {
2079
- "content": "<extra_id_254>",
2080
- "lstrip": false,
2081
- "normalized": false,
2082
- "rstrip": false,
2083
- "single_word": false,
2084
- "special": false
2085
- },
2086
- "260": {
2087
- "content": "<extra_id_255>",
2088
- "lstrip": false,
2089
- "normalized": false,
2090
- "rstrip": false,
2091
- "single_word": false,
2092
- "special": false
2093
  }
2094
  },
2095
  "bos_token": "<s>",
 
42
  "rstrip": false,
43
  "single_word": false,
44
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
45
  }
46
  },
47
  "bos_token": "<s>",