sagawa commited on
Commit
f7d903c
1 Parent(s): bfb2b90

Upload tokenizer.json

Browse files
Files changed (1) hide show
  1. tokenizer.json +1507 -0
tokenizer.json ADDED
@@ -0,0 +1,1507 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<pad>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "</s>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<unk>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 121,
35
+ "content": "<extra_id_0>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 122,
44
+ "content": "<extra_id_1>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 123,
53
+ "content": "<extra_id_2>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 124,
62
+ "content": "<extra_id_3>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 125,
71
+ "content": "<extra_id_4>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 126,
80
+ "content": "<extra_id_5>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 127,
89
+ "content": "<extra_id_6>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 128,
98
+ "content": "<extra_id_7>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 129,
107
+ "content": "<extra_id_8>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 130,
116
+ "content": "<extra_id_9>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 131,
125
+ "content": "<extra_id_10>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 132,
134
+ "content": "<extra_id_11>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 133,
143
+ "content": "<extra_id_12>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 134,
152
+ "content": "<extra_id_13>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 135,
161
+ "content": "<extra_id_14>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 136,
170
+ "content": "<extra_id_15>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 137,
179
+ "content": "<extra_id_16>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 138,
188
+ "content": "<extra_id_17>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 139,
197
+ "content": "<extra_id_18>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 140,
206
+ "content": "<extra_id_19>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 141,
215
+ "content": "<extra_id_20>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 142,
224
+ "content": "<extra_id_21>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 143,
233
+ "content": "<extra_id_22>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 144,
242
+ "content": "<extra_id_23>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 145,
251
+ "content": "<extra_id_24>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 146,
260
+ "content": "<extra_id_25>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 147,
269
+ "content": "<extra_id_26>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 148,
278
+ "content": "<extra_id_27>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 149,
287
+ "content": "<extra_id_28>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 150,
296
+ "content": "<extra_id_29>",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 151,
305
+ "content": "<extra_id_30>",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 152,
314
+ "content": "<extra_id_31>",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 153,
323
+ "content": "<extra_id_32>",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 154,
332
+ "content": "<extra_id_33>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 155,
341
+ "content": "<extra_id_34>",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 156,
350
+ "content": "<extra_id_35>",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 157,
359
+ "content": "<extra_id_36>",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 158,
368
+ "content": "<extra_id_37>",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 159,
377
+ "content": "<extra_id_38>",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 160,
386
+ "content": "<extra_id_39>",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 161,
395
+ "content": "<extra_id_40>",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 162,
404
+ "content": "<extra_id_41>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 163,
413
+ "content": "<extra_id_42>",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 164,
422
+ "content": "<extra_id_43>",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 165,
431
+ "content": "<extra_id_44>",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
+ },
438
+ {
439
+ "id": 166,
440
+ "content": "<extra_id_45>",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
+ },
447
+ {
448
+ "id": 167,
449
+ "content": "<extra_id_46>",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": false,
454
+ "special": true
455
+ },
456
+ {
457
+ "id": 168,
458
+ "content": "<extra_id_47>",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": false,
463
+ "special": true
464
+ },
465
+ {
466
+ "id": 169,
467
+ "content": "<extra_id_48>",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": false,
472
+ "special": true
473
+ },
474
+ {
475
+ "id": 170,
476
+ "content": "<extra_id_49>",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": false,
481
+ "special": true
482
+ },
483
+ {
484
+ "id": 171,
485
+ "content": "<extra_id_50>",
486
+ "single_word": false,
487
+ "lstrip": false,
488
+ "rstrip": false,
489
+ "normalized": false,
490
+ "special": true
491
+ },
492
+ {
493
+ "id": 172,
494
+ "content": "<extra_id_51>",
495
+ "single_word": false,
496
+ "lstrip": false,
497
+ "rstrip": false,
498
+ "normalized": false,
499
+ "special": true
500
+ },
501
+ {
502
+ "id": 173,
503
+ "content": "<extra_id_52>",
504
+ "single_word": false,
505
+ "lstrip": false,
506
+ "rstrip": false,
507
+ "normalized": false,
508
+ "special": true
509
+ },
510
+ {
511
+ "id": 174,
512
+ "content": "<extra_id_53>",
513
+ "single_word": false,
514
+ "lstrip": false,
515
+ "rstrip": false,
516
+ "normalized": false,
517
+ "special": true
518
+ },
519
+ {
520
+ "id": 175,
521
+ "content": "<extra_id_54>",
522
+ "single_word": false,
523
+ "lstrip": false,
524
+ "rstrip": false,
525
+ "normalized": false,
526
+ "special": true
527
+ },
528
+ {
529
+ "id": 176,
530
+ "content": "<extra_id_55>",
531
+ "single_word": false,
532
+ "lstrip": false,
533
+ "rstrip": false,
534
+ "normalized": false,
535
+ "special": true
536
+ },
537
+ {
538
+ "id": 177,
539
+ "content": "<extra_id_56>",
540
+ "single_word": false,
541
+ "lstrip": false,
542
+ "rstrip": false,
543
+ "normalized": false,
544
+ "special": true
545
+ },
546
+ {
547
+ "id": 178,
548
+ "content": "<extra_id_57>",
549
+ "single_word": false,
550
+ "lstrip": false,
551
+ "rstrip": false,
552
+ "normalized": false,
553
+ "special": true
554
+ },
555
+ {
556
+ "id": 179,
557
+ "content": "<extra_id_58>",
558
+ "single_word": false,
559
+ "lstrip": false,
560
+ "rstrip": false,
561
+ "normalized": false,
562
+ "special": true
563
+ },
564
+ {
565
+ "id": 180,
566
+ "content": "<extra_id_59>",
567
+ "single_word": false,
568
+ "lstrip": false,
569
+ "rstrip": false,
570
+ "normalized": false,
571
+ "special": true
572
+ },
573
+ {
574
+ "id": 181,
575
+ "content": "<extra_id_60>",
576
+ "single_word": false,
577
+ "lstrip": false,
578
+ "rstrip": false,
579
+ "normalized": false,
580
+ "special": true
581
+ },
582
+ {
583
+ "id": 182,
584
+ "content": "<extra_id_61>",
585
+ "single_word": false,
586
+ "lstrip": false,
587
+ "rstrip": false,
588
+ "normalized": false,
589
+ "special": true
590
+ },
591
+ {
592
+ "id": 183,
593
+ "content": "<extra_id_62>",
594
+ "single_word": false,
595
+ "lstrip": false,
596
+ "rstrip": false,
597
+ "normalized": false,
598
+ "special": true
599
+ },
600
+ {
601
+ "id": 184,
602
+ "content": "<extra_id_63>",
603
+ "single_word": false,
604
+ "lstrip": false,
605
+ "rstrip": false,
606
+ "normalized": false,
607
+ "special": true
608
+ },
609
+ {
610
+ "id": 185,
611
+ "content": "<extra_id_64>",
612
+ "single_word": false,
613
+ "lstrip": false,
614
+ "rstrip": false,
615
+ "normalized": false,
616
+ "special": true
617
+ },
618
+ {
619
+ "id": 186,
620
+ "content": "<extra_id_65>",
621
+ "single_word": false,
622
+ "lstrip": false,
623
+ "rstrip": false,
624
+ "normalized": false,
625
+ "special": true
626
+ },
627
+ {
628
+ "id": 187,
629
+ "content": "<extra_id_66>",
630
+ "single_word": false,
631
+ "lstrip": false,
632
+ "rstrip": false,
633
+ "normalized": false,
634
+ "special": true
635
+ },
636
+ {
637
+ "id": 188,
638
+ "content": "<extra_id_67>",
639
+ "single_word": false,
640
+ "lstrip": false,
641
+ "rstrip": false,
642
+ "normalized": false,
643
+ "special": true
644
+ },
645
+ {
646
+ "id": 189,
647
+ "content": "<extra_id_68>",
648
+ "single_word": false,
649
+ "lstrip": false,
650
+ "rstrip": false,
651
+ "normalized": false,
652
+ "special": true
653
+ },
654
+ {
655
+ "id": 190,
656
+ "content": "<extra_id_69>",
657
+ "single_word": false,
658
+ "lstrip": false,
659
+ "rstrip": false,
660
+ "normalized": false,
661
+ "special": true
662
+ },
663
+ {
664
+ "id": 191,
665
+ "content": "<extra_id_70>",
666
+ "single_word": false,
667
+ "lstrip": false,
668
+ "rstrip": false,
669
+ "normalized": false,
670
+ "special": true
671
+ },
672
+ {
673
+ "id": 192,
674
+ "content": "<extra_id_71>",
675
+ "single_word": false,
676
+ "lstrip": false,
677
+ "rstrip": false,
678
+ "normalized": false,
679
+ "special": true
680
+ },
681
+ {
682
+ "id": 193,
683
+ "content": "<extra_id_72>",
684
+ "single_word": false,
685
+ "lstrip": false,
686
+ "rstrip": false,
687
+ "normalized": false,
688
+ "special": true
689
+ },
690
+ {
691
+ "id": 194,
692
+ "content": "<extra_id_73>",
693
+ "single_word": false,
694
+ "lstrip": false,
695
+ "rstrip": false,
696
+ "normalized": false,
697
+ "special": true
698
+ },
699
+ {
700
+ "id": 195,
701
+ "content": "<extra_id_74>",
702
+ "single_word": false,
703
+ "lstrip": false,
704
+ "rstrip": false,
705
+ "normalized": false,
706
+ "special": true
707
+ },
708
+ {
709
+ "id": 196,
710
+ "content": "<extra_id_75>",
711
+ "single_word": false,
712
+ "lstrip": false,
713
+ "rstrip": false,
714
+ "normalized": false,
715
+ "special": true
716
+ },
717
+ {
718
+ "id": 197,
719
+ "content": "<extra_id_76>",
720
+ "single_word": false,
721
+ "lstrip": false,
722
+ "rstrip": false,
723
+ "normalized": false,
724
+ "special": true
725
+ },
726
+ {
727
+ "id": 198,
728
+ "content": "<extra_id_77>",
729
+ "single_word": false,
730
+ "lstrip": false,
731
+ "rstrip": false,
732
+ "normalized": false,
733
+ "special": true
734
+ },
735
+ {
736
+ "id": 199,
737
+ "content": "<extra_id_78>",
738
+ "single_word": false,
739
+ "lstrip": false,
740
+ "rstrip": false,
741
+ "normalized": false,
742
+ "special": true
743
+ },
744
+ {
745
+ "id": 200,
746
+ "content": "<extra_id_79>",
747
+ "single_word": false,
748
+ "lstrip": false,
749
+ "rstrip": false,
750
+ "normalized": false,
751
+ "special": true
752
+ },
753
+ {
754
+ "id": 201,
755
+ "content": "<extra_id_80>",
756
+ "single_word": false,
757
+ "lstrip": false,
758
+ "rstrip": false,
759
+ "normalized": false,
760
+ "special": true
761
+ },
762
+ {
763
+ "id": 202,
764
+ "content": "<extra_id_81>",
765
+ "single_word": false,
766
+ "lstrip": false,
767
+ "rstrip": false,
768
+ "normalized": false,
769
+ "special": true
770
+ },
771
+ {
772
+ "id": 203,
773
+ "content": "<extra_id_82>",
774
+ "single_word": false,
775
+ "lstrip": false,
776
+ "rstrip": false,
777
+ "normalized": false,
778
+ "special": true
779
+ },
780
+ {
781
+ "id": 204,
782
+ "content": "<extra_id_83>",
783
+ "single_word": false,
784
+ "lstrip": false,
785
+ "rstrip": false,
786
+ "normalized": false,
787
+ "special": true
788
+ },
789
+ {
790
+ "id": 205,
791
+ "content": "<extra_id_84>",
792
+ "single_word": false,
793
+ "lstrip": false,
794
+ "rstrip": false,
795
+ "normalized": false,
796
+ "special": true
797
+ },
798
+ {
799
+ "id": 206,
800
+ "content": "<extra_id_85>",
801
+ "single_word": false,
802
+ "lstrip": false,
803
+ "rstrip": false,
804
+ "normalized": false,
805
+ "special": true
806
+ },
807
+ {
808
+ "id": 207,
809
+ "content": "<extra_id_86>",
810
+ "single_word": false,
811
+ "lstrip": false,
812
+ "rstrip": false,
813
+ "normalized": false,
814
+ "special": true
815
+ },
816
+ {
817
+ "id": 208,
818
+ "content": "<extra_id_87>",
819
+ "single_word": false,
820
+ "lstrip": false,
821
+ "rstrip": false,
822
+ "normalized": false,
823
+ "special": true
824
+ },
825
+ {
826
+ "id": 209,
827
+ "content": "<extra_id_88>",
828
+ "single_word": false,
829
+ "lstrip": false,
830
+ "rstrip": false,
831
+ "normalized": false,
832
+ "special": true
833
+ },
834
+ {
835
+ "id": 210,
836
+ "content": "<extra_id_89>",
837
+ "single_word": false,
838
+ "lstrip": false,
839
+ "rstrip": false,
840
+ "normalized": false,
841
+ "special": true
842
+ },
843
+ {
844
+ "id": 211,
845
+ "content": "<extra_id_90>",
846
+ "single_word": false,
847
+ "lstrip": false,
848
+ "rstrip": false,
849
+ "normalized": false,
850
+ "special": true
851
+ },
852
+ {
853
+ "id": 212,
854
+ "content": "<extra_id_91>",
855
+ "single_word": false,
856
+ "lstrip": false,
857
+ "rstrip": false,
858
+ "normalized": false,
859
+ "special": true
860
+ },
861
+ {
862
+ "id": 213,
863
+ "content": "<extra_id_92>",
864
+ "single_word": false,
865
+ "lstrip": false,
866
+ "rstrip": false,
867
+ "normalized": false,
868
+ "special": true
869
+ },
870
+ {
871
+ "id": 214,
872
+ "content": "<extra_id_93>",
873
+ "single_word": false,
874
+ "lstrip": false,
875
+ "rstrip": false,
876
+ "normalized": false,
877
+ "special": true
878
+ },
879
+ {
880
+ "id": 215,
881
+ "content": "<extra_id_94>",
882
+ "single_word": false,
883
+ "lstrip": false,
884
+ "rstrip": false,
885
+ "normalized": false,
886
+ "special": true
887
+ },
888
+ {
889
+ "id": 216,
890
+ "content": "<extra_id_95>",
891
+ "single_word": false,
892
+ "lstrip": false,
893
+ "rstrip": false,
894
+ "normalized": false,
895
+ "special": true
896
+ },
897
+ {
898
+ "id": 217,
899
+ "content": "<extra_id_96>",
900
+ "single_word": false,
901
+ "lstrip": false,
902
+ "rstrip": false,
903
+ "normalized": false,
904
+ "special": true
905
+ },
906
+ {
907
+ "id": 218,
908
+ "content": "<extra_id_97>",
909
+ "single_word": false,
910
+ "lstrip": false,
911
+ "rstrip": false,
912
+ "normalized": false,
913
+ "special": true
914
+ },
915
+ {
916
+ "id": 219,
917
+ "content": "<extra_id_98>",
918
+ "single_word": false,
919
+ "lstrip": false,
920
+ "rstrip": false,
921
+ "normalized": false,
922
+ "special": true
923
+ },
924
+ {
925
+ "id": 220,
926
+ "content": "<extra_id_99>",
927
+ "single_word": false,
928
+ "lstrip": false,
929
+ "rstrip": false,
930
+ "normalized": false,
931
+ "special": true
932
+ }
933
+ ],
934
+ "normalizer": {
935
+ "type": "Sequence",
936
+ "normalizers": [
937
+ {
938
+ "type": "Nmt"
939
+ },
940
+ {
941
+ "type": "NFKC"
942
+ },
943
+ {
944
+ "type": "Replace",
945
+ "pattern": {
946
+ "Regex": " {2,}"
947
+ },
948
+ "content": " "
949
+ }
950
+ ]
951
+ },
952
+ "pre_tokenizer": {
953
+ "type": "Sequence",
954
+ "pretokenizers": [
955
+ {
956
+ "type": "Metaspace",
957
+ "replacement": "▁",
958
+ "add_prefix_space": true
959
+ },
960
+ {
961
+ "type": "Digits",
962
+ "individual_digits": true
963
+ },
964
+ {
965
+ "type": "Punctuation",
966
+ "behavior": "Isolated"
967
+ }
968
+ ]
969
+ },
970
+ "post_processor": {
971
+ "type": "TemplateProcessing",
972
+ "single": [
973
+ {
974
+ "Sequence": {
975
+ "id": "A",
976
+ "type_id": 0
977
+ }
978
+ },
979
+ {
980
+ "SpecialToken": {
981
+ "id": "</s>",
982
+ "type_id": 0
983
+ }
984
+ }
985
+ ],
986
+ "pair": [
987
+ {
988
+ "Sequence": {
989
+ "id": "A",
990
+ "type_id": 0
991
+ }
992
+ },
993
+ {
994
+ "Sequence": {
995
+ "id": "B",
996
+ "type_id": 1
997
+ }
998
+ }
999
+ ],
1000
+ "special_tokens": {
1001
+ "</s>": {
1002
+ "id": "</s>",
1003
+ "ids": [
1004
+ 1
1005
+ ],
1006
+ "tokens": [
1007
+ "</s>"
1008
+ ]
1009
+ }
1010
+ }
1011
+ },
1012
+ "decoder": {
1013
+ "type": "Metaspace",
1014
+ "replacement": "▁",
1015
+ "add_prefix_space": true
1016
+ },
1017
+ "model": {
1018
+ "type": "Unigram",
1019
+ "unk_id": 2,
1020
+ "vocab": [
1021
+ [
1022
+ "<pad>",
1023
+ 0.0
1024
+ ],
1025
+ [
1026
+ "</s>",
1027
+ 0.0
1028
+ ],
1029
+ [
1030
+ "<unk>",
1031
+ 0.0
1032
+ ],
1033
+ [
1034
+ "C",
1035
+ -1.934062026530869
1036
+ ],
1037
+ [
1038
+ "c",
1039
+ -2.005135123981896
1040
+ ],
1041
+ [
1042
+ ")",
1043
+ -2.3305416341016603
1044
+ ],
1045
+ [
1046
+ "(",
1047
+ -2.3305416341016603
1048
+ ],
1049
+ [
1050
+ "1",
1051
+ -2.659489340254079
1052
+ ],
1053
+ [
1054
+ "2",
1055
+ -3.0147314517826524
1056
+ ],
1057
+ [
1058
+ "O",
1059
+ -3.1705660462226426
1060
+ ],
1061
+ [
1062
+ "]",
1063
+ -3.306692943444802
1064
+ ],
1065
+ [
1066
+ "[",
1067
+ -3.306692943444802
1068
+ ],
1069
+ [
1070
+ "N",
1071
+ -3.3379525475363145
1072
+ ],
1073
+ [
1074
+ "@",
1075
+ -3.375613737475505
1076
+ ],
1077
+ [
1078
+ "H",
1079
+ -3.3960003181228675
1080
+ ],
1081
+ [
1082
+ "=",
1083
+ -3.4342358584336026
1084
+ ],
1085
+ [
1086
+ "n",
1087
+ -3.9996436484078535
1088
+ ],
1089
+ [
1090
+ "3",
1091
+ -4.06624150723795
1092
+ ],
1093
+ [
1094
+ "+",
1095
+ -4.576587821405814
1096
+ ],
1097
+ [
1098
+ "ccc",
1099
+ -4.581329068949029
1100
+ ],
1101
+ [
1102
+ "cccc",
1103
+ -4.794168477161054
1104
+ ],
1105
+ [
1106
+ "F",
1107
+ -4.844444469349959
1108
+ ],
1109
+ [
1110
+ "▁C",
1111
+ -4.930731418706828
1112
+ ],
1113
+ [
1114
+ "-",
1115
+ -5.128151794820781
1116
+ ],
1117
+ [
1118
+ "CC",
1119
+ -5.188054847421637
1120
+ ],
1121
+ [
1122
+ "▁",
1123
+ -5.243375183264384
1124
+ ],
1125
+ [
1126
+ "▁CC",
1127
+ -5.43665410318811
1128
+ ],
1129
+ [
1130
+ "cc",
1131
+ -5.5072446210190025
1132
+ ],
1133
+ [
1134
+ "S",
1135
+ -5.607990514129369
1136
+ ],
1137
+ [
1138
+ "CCC",
1139
+ -5.610845771534942
1140
+ ],
1141
+ [
1142
+ "4",
1143
+ -5.6728058623804705
1144
+ ],
1145
+ [
1146
+ "CCN",
1147
+ -5.984229431727735
1148
+ ],
1149
+ [
1150
+ "▁CO",
1151
+ -6.136725098692515
1152
+ ],
1153
+ [
1154
+ "s",
1155
+ -6.163972117410355
1156
+ ],
1157
+ [
1158
+ "l",
1159
+ -6.244242813422005
1160
+ ],
1161
+ [
1162
+ "nc",
1163
+ -6.260369976115332
1164
+ ],
1165
+ [
1166
+ "Cl",
1167
+ -6.29041030199948
1168
+ ],
1169
+ [
1170
+ "NC",
1171
+ -6.301741325285667
1172
+ ],
1173
+ [
1174
+ "#",
1175
+ -6.475695381808137
1176
+ ],
1177
+ [
1178
+ "CCCC",
1179
+ -6.630889749196982
1180
+ ],
1181
+ [
1182
+ "Br",
1183
+ -6.708882955827546
1184
+ ],
1185
+ [
1186
+ "o",
1187
+ -6.8821690990922
1188
+ ],
1189
+ [
1190
+ "no",
1191
+ -7.085301372799254
1192
+ ],
1193
+ [
1194
+ "nn",
1195
+ -7.118314757276033
1196
+ ],
1197
+ [
1198
+ "CN",
1199
+ -7.148023077707199
1200
+ ],
1201
+ [
1202
+ "▁O",
1203
+ -7.184905330255651
1204
+ ],
1205
+ [
1206
+ "CCO",
1207
+ -7.223262672570243
1208
+ ],
1209
+ [
1210
+ "▁CN",
1211
+ -7.340957119808042
1212
+ ],
1213
+ [
1214
+ "ccs",
1215
+ -7.358439269448935
1216
+ ],
1217
+ [
1218
+ "▁CCC",
1219
+ -7.384181818093239
1220
+ ],
1221
+ [
1222
+ "OC",
1223
+ -7.401588967543117
1224
+ ],
1225
+ [
1226
+ "/",
1227
+ -7.412130091887384
1228
+ ],
1229
+ [
1230
+ "▁COC",
1231
+ -7.453342081307827
1232
+ ],
1233
+ [
1234
+ "nnc",
1235
+ -7.47808245293119
1236
+ ],
1237
+ [
1238
+ "cccn",
1239
+ -7.526117466256242
1240
+ ],
1241
+ [
1242
+ "▁CCOC",
1243
+ -7.581460400684973
1244
+ ],
1245
+ [
1246
+ "sc",
1247
+ -7.587476370908391
1248
+ ],
1249
+ [
1250
+ "cco",
1251
+ -7.601812309424911
1252
+ ],
1253
+ [
1254
+ "CCOCC",
1255
+ -7.70962259415791
1256
+ ],
1257
+ [
1258
+ "CCCN",
1259
+ -7.716050546596486
1260
+ ],
1261
+ [
1262
+ "oc",
1263
+ -7.76950331715161
1264
+ ],
1265
+ [
1266
+ "ccnc",
1267
+ -7.885377075776418
1268
+ ],
1269
+ [
1270
+ "▁CCO",
1271
+ -7.958354042052764
1272
+ ],
1273
+ [
1274
+ "cs",
1275
+ -7.963618836898841
1276
+ ],
1277
+ [
1278
+ "▁CCN",
1279
+ -7.969745690077621
1280
+ ],
1281
+ [
1282
+ "NCC",
1283
+ -7.982831223650715
1284
+ ],
1285
+ [
1286
+ "CNC",
1287
+ -8.015812540478317
1288
+ ],
1289
+ [
1290
+ "CCCO",
1291
+ -8.02283744281797
1292
+ ],
1293
+ [
1294
+ "nccn",
1295
+ -8.023781204384559
1296
+ ],
1297
+ [
1298
+ "CCCCC",
1299
+ -8.113410349713947
1300
+ ],
1301
+ [
1302
+ "csc",
1303
+ -8.123340128859317
1304
+ ],
1305
+ [
1306
+ "nnn",
1307
+ -8.16923209155111
1308
+ ],
1309
+ [
1310
+ "CO",
1311
+ -8.197076591417558
1312
+ ],
1313
+ [
1314
+ "cnc",
1315
+ -8.24948897316689
1316
+ ],
1317
+ [
1318
+ "OCC",
1319
+ -8.337244843539168
1320
+ ],
1321
+ [
1322
+ "ncc",
1323
+ -8.35350988501787
1324
+ ],
1325
+ [
1326
+ "CCNC",
1327
+ -8.374584543880331
1328
+ ],
1329
+ [
1330
+ "cnn",
1331
+ -8.379764985534148
1332
+ ],
1333
+ [
1334
+ "▁CCCC",
1335
+ -8.408946579060395
1336
+ ],
1337
+ [
1338
+ "ccn",
1339
+ -8.441316367356151
1340
+ ],
1341
+ [
1342
+ "▁CCCN",
1343
+ -8.455940453267049
1344
+ ],
1345
+ [
1346
+ "ncn",
1347
+ -8.509281787409483
1348
+ ],
1349
+ [
1350
+ "CCOC",
1351
+ -8.545791064619086
1352
+ ],
1353
+ [
1354
+ "5",
1355
+ -8.595231126796552
1356
+ ],
1357
+ [
1358
+ "OCCO",
1359
+ -8.620568633537287
1360
+ ],
1361
+ [
1362
+ "SCC",
1363
+ -8.675945846432537
1364
+ ],
1365
+ [
1366
+ "\\",
1367
+ -8.738088269693655
1368
+ ],
1369
+ [
1370
+ "▁CS",
1371
+ -8.745760398405787
1372
+ ],
1373
+ [
1374
+ "cn",
1375
+ -8.81287462848524
1376
+ ],
1377
+ [
1378
+ "CS",
1379
+ -8.852680543942768
1380
+ ],
1381
+ [
1382
+ "COC",
1383
+ -8.901532120821837
1384
+ ],
1385
+ [
1386
+ "▁CCCO",
1387
+ -8.971729419021525
1388
+ ],
1389
+ [
1390
+ "▁COCC",
1391
+ -8.986602855501445
1392
+ ],
1393
+ [
1394
+ "▁F",
1395
+ -9.08172188898926
1396
+ ],
1397
+ [
1398
+ "▁CCNC",
1399
+ -9.213239929783953
1400
+ ],
1401
+ [
1402
+ "nccc",
1403
+ -9.267617565078302
1404
+ ],
1405
+ [
1406
+ "▁CCS",
1407
+ -9.284123840101111
1408
+ ],
1409
+ [
1410
+ "▁N",
1411
+ -9.46465900903722
1412
+ ],
1413
+ [
1414
+ "▁CCCCO",
1415
+ -9.549659454320029
1416
+ ],
1417
+ [
1418
+ "NCCC",
1419
+ -9.592808545839064
1420
+ ],
1421
+ [
1422
+ "NCCN",
1423
+ -9.616093114468232
1424
+ ],
1425
+ [
1426
+ "CCS",
1427
+ -9.68568843530331
1428
+ ],
1429
+ [
1430
+ "cncc",
1431
+ -9.884757958758378
1432
+ ],
1433
+ [
1434
+ "CCCS",
1435
+ -10.07490132384844
1436
+ ],
1437
+ [
1438
+ "▁NC",
1439
+ -10.174180411834037
1440
+ ],
1441
+ [
1442
+ "▁COCCN",
1443
+ -10.182867019690027
1444
+ ],
1445
+ [
1446
+ "▁COCCO",
1447
+ -10.210382702506402
1448
+ ],
1449
+ [
1450
+ "▁COCCC",
1451
+ -10.390960567106395
1452
+ ],
1453
+ [
1454
+ "OCO",
1455
+ -10.445584736697652
1456
+ ],
1457
+ [
1458
+ "COCC",
1459
+ -10.469925833149428
1460
+ ],
1461
+ [
1462
+ "▁CCOCCN",
1463
+ -10.487938027145828
1464
+ ],
1465
+ [
1466
+ "SC",
1467
+ -10.868655865451124
1468
+ ],
1469
+ [
1470
+ "co",
1471
+ -11.175046369147724
1472
+ ],
1473
+ [
1474
+ "I",
1475
+ -11.188088269693656
1476
+ ],
1477
+ [
1478
+ "on",
1479
+ -11.199838029113598
1480
+ ],
1481
+ [
1482
+ "CCCCN",
1483
+ -11.273835881601958
1484
+ ],
1485
+ [
1486
+ "▁CCCCN",
1487
+ -11.694782342260607
1488
+ ],
1489
+ [
1490
+ "CCOCCN",
1491
+ -11.98760417613926
1492
+ ],
1493
+ [
1494
+ "r",
1495
+ -12.313357692926305
1496
+ ],
1497
+ [
1498
+ "B",
1499
+ -12.313457692926304
1500
+ ],
1501
+ [
1502
+ "CCCCO",
1503
+ -12.313457692926304
1504
+ ]
1505
+ ]
1506
+ }
1507
+ }