gsaltintas commited on
Commit
78b1942
·
verified ·
1 Parent(s): 3dd1eb9

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. merges.txt +0 -90
  3. tokenizer.json +841 -465
  4. tokenizer_config.json +744 -0
  5. vocab.json +104 -104
README.md CHANGED
@@ -46,4 +46,4 @@ tokens = tokenizer.encode("Hello, world!")
46
  ## Sample Encoding
47
  | Text | Tokens | Token IDs |
48
  |------|--------|-----------|
49
- | `1234500119 mod 67` | `12, 34, 50, 0, 1, 19, , mod, , 67` | `19, 41, 57, 7, 8, 26, 6, 4, 6, 74` |
 
46
  ## Sample Encoding
47
  | Text | Tokens | Token IDs |
48
  |------|--------|-----------|
49
+ | `1234500119 mod 67` | `12, 34, 50, 0, 11, 9, , mod, , 67` | `65, 74, 35, 8, 7, 21, 6, 4, 6, 62` |
merges.txt CHANGED
@@ -1,91 +1 @@
1
  #version: 0.2
2
- ['1', '0']
3
- ['1', '1']
4
- ['1', '2']
5
- ['1', '3']
6
- ['1', '4']
7
- ['1', '5']
8
- ['1', '6']
9
- ['1', '7']
10
- ['1', '8']
11
- ['1', '9']
12
- ['2', '0']
13
- ['2', '1']
14
- ['2', '2']
15
- ['2', '3']
16
- ['2', '4']
17
- ['2', '5']
18
- ['2', '6']
19
- ['2', '7']
20
- ['2', '8']
21
- ['2', '9']
22
- ['3', '0']
23
- ['3', '1']
24
- ['3', '2']
25
- ['3', '3']
26
- ['3', '4']
27
- ['3', '5']
28
- ['3', '6']
29
- ['3', '7']
30
- ['3', '8']
31
- ['3', '9']
32
- ['4', '0']
33
- ['4', '1']
34
- ['4', '2']
35
- ['4', '3']
36
- ['4', '4']
37
- ['4', '5']
38
- ['4', '6']
39
- ['4', '7']
40
- ['4', '8']
41
- ['4', '9']
42
- ['5', '0']
43
- ['5', '1']
44
- ['5', '2']
45
- ['5', '3']
46
- ['5', '4']
47
- ['5', '5']
48
- ['5', '6']
49
- ['5', '7']
50
- ['5', '8']
51
- ['5', '9']
52
- ['6', '0']
53
- ['6', '1']
54
- ['6', '2']
55
- ['6', '3']
56
- ['6', '4']
57
- ['6', '5']
58
- ['6', '6']
59
- ['6', '7']
60
- ['6', '8']
61
- ['6', '9']
62
- ['7', '0']
63
- ['7', '1']
64
- ['7', '2']
65
- ['7', '3']
66
- ['7', '4']
67
- ['7', '5']
68
- ['7', '6']
69
- ['7', '7']
70
- ['7', '8']
71
- ['7', '9']
72
- ['8', '0']
73
- ['8', '1']
74
- ['8', '2']
75
- ['8', '3']
76
- ['8', '4']
77
- ['8', '5']
78
- ['8', '6']
79
- ['8', '7']
80
- ['8', '8']
81
- ['8', '9']
82
- ['9', '0']
83
- ['9', '1']
84
- ['9', '2']
85
- ['9', '3']
86
- ['9', '4']
87
- ['9', '5']
88
- ['9', '6']
89
- ['9', '7']
90
- ['9', '8']
91
- ['9', '9']
 
1
  #version: 0.2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
tokenizer.json CHANGED
@@ -65,6 +65,843 @@
65
  "rstrip": false,
66
  "normalized": false,
67
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
68
  }
69
  ],
70
  "normalizer": null,
@@ -83,7 +920,7 @@
83
  "type": "ByteLevel",
84
  "add_prefix_space": false,
85
  "trim_offsets": true,
86
- "use_regex": true
87
  }
88
  ]
89
  },
@@ -110,469 +947,8 @@
110
  "<pad>": 3,
111
  "mod": 4,
112
  "=": 5,
113
- " ": 6,
114
- "0": 7,
115
- "1": 8,
116
- "2": 9,
117
- "3": 10,
118
- "4": 11,
119
- "5": 12,
120
- "6": 13,
121
- "7": 14,
122
- "8": 15,
123
- "9": 16,
124
- "10": 17,
125
- "11": 18,
126
- "12": 19,
127
- "13": 20,
128
- "14": 21,
129
- "15": 22,
130
- "16": 23,
131
- "17": 24,
132
- "18": 25,
133
- "19": 26,
134
- "20": 27,
135
- "21": 28,
136
- "22": 29,
137
- "23": 30,
138
- "24": 31,
139
- "25": 32,
140
- "26": 33,
141
- "27": 34,
142
- "28": 35,
143
- "29": 36,
144
- "30": 37,
145
- "31": 38,
146
- "32": 39,
147
- "33": 40,
148
- "34": 41,
149
- "35": 42,
150
- "36": 43,
151
- "37": 44,
152
- "38": 45,
153
- "39": 46,
154
- "40": 47,
155
- "41": 48,
156
- "42": 49,
157
- "43": 50,
158
- "44": 51,
159
- "45": 52,
160
- "46": 53,
161
- "47": 54,
162
- "48": 55,
163
- "49": 56,
164
- "50": 57,
165
- "51": 58,
166
- "52": 59,
167
- "53": 60,
168
- "54": 61,
169
- "55": 62,
170
- "56": 63,
171
- "57": 64,
172
- "58": 65,
173
- "59": 66,
174
- "60": 67,
175
- "61": 68,
176
- "62": 69,
177
- "63": 70,
178
- "64": 71,
179
- "65": 72,
180
- "66": 73,
181
- "67": 74,
182
- "68": 75,
183
- "69": 76,
184
- "70": 77,
185
- "71": 78,
186
- "72": 79,
187
- "73": 80,
188
- "74": 81,
189
- "75": 82,
190
- "76": 83,
191
- "77": 84,
192
- "78": 85,
193
- "79": 86,
194
- "80": 87,
195
- "81": 88,
196
- "82": 89,
197
- "83": 90,
198
- "84": 91,
199
- "85": 92,
200
- "86": 93,
201
- "87": 94,
202
- "88": 95,
203
- "89": 96,
204
- "90": 97,
205
- "91": 98,
206
- "92": 99,
207
- "93": 100,
208
- "94": 101,
209
- "95": 102,
210
- "96": 103,
211
- "97": 104,
212
- "98": 105,
213
- "99": 106
214
- },
215
- "merges": [
216
- [
217
- "1",
218
- "0"
219
- ],
220
- [
221
- "1",
222
- "1"
223
- ],
224
- [
225
- "1",
226
- "2"
227
- ],
228
- [
229
- "1",
230
- "3"
231
- ],
232
- [
233
- "1",
234
- "4"
235
- ],
236
- [
237
- "1",
238
- "5"
239
- ],
240
- [
241
- "1",
242
- "6"
243
- ],
244
- [
245
- "1",
246
- "7"
247
- ],
248
- [
249
- "1",
250
- "8"
251
- ],
252
- [
253
- "1",
254
- "9"
255
- ],
256
- [
257
- "2",
258
- "0"
259
- ],
260
- [
261
- "2",
262
- "1"
263
- ],
264
- [
265
- "2",
266
- "2"
267
- ],
268
- [
269
- "2",
270
- "3"
271
- ],
272
- [
273
- "2",
274
- "4"
275
- ],
276
- [
277
- "2",
278
- "5"
279
- ],
280
- [
281
- "2",
282
- "6"
283
- ],
284
- [
285
- "2",
286
- "7"
287
- ],
288
- [
289
- "2",
290
- "8"
291
- ],
292
- [
293
- "2",
294
- "9"
295
- ],
296
- [
297
- "3",
298
- "0"
299
- ],
300
- [
301
- "3",
302
- "1"
303
- ],
304
- [
305
- "3",
306
- "2"
307
- ],
308
- [
309
- "3",
310
- "3"
311
- ],
312
- [
313
- "3",
314
- "4"
315
- ],
316
- [
317
- "3",
318
- "5"
319
- ],
320
- [
321
- "3",
322
- "6"
323
- ],
324
- [
325
- "3",
326
- "7"
327
- ],
328
- [
329
- "3",
330
- "8"
331
- ],
332
- [
333
- "3",
334
- "9"
335
- ],
336
- [
337
- "4",
338
- "0"
339
- ],
340
- [
341
- "4",
342
- "1"
343
- ],
344
- [
345
- "4",
346
- "2"
347
- ],
348
- [
349
- "4",
350
- "3"
351
- ],
352
- [
353
- "4",
354
- "4"
355
- ],
356
- [
357
- "4",
358
- "5"
359
- ],
360
- [
361
- "4",
362
- "6"
363
- ],
364
- [
365
- "4",
366
- "7"
367
- ],
368
- [
369
- "4",
370
- "8"
371
- ],
372
- [
373
- "4",
374
- "9"
375
- ],
376
- [
377
- "5",
378
- "0"
379
- ],
380
- [
381
- "5",
382
- "1"
383
- ],
384
- [
385
- "5",
386
- "2"
387
- ],
388
- [
389
- "5",
390
- "3"
391
- ],
392
- [
393
- "5",
394
- "4"
395
- ],
396
- [
397
- "5",
398
- "5"
399
- ],
400
- [
401
- "5",
402
- "6"
403
- ],
404
- [
405
- "5",
406
- "7"
407
- ],
408
- [
409
- "5",
410
- "8"
411
- ],
412
- [
413
- "5",
414
- "9"
415
- ],
416
- [
417
- "6",
418
- "0"
419
- ],
420
- [
421
- "6",
422
- "1"
423
- ],
424
- [
425
- "6",
426
- "2"
427
- ],
428
- [
429
- "6",
430
- "3"
431
- ],
432
- [
433
- "6",
434
- "4"
435
- ],
436
- [
437
- "6",
438
- "5"
439
- ],
440
- [
441
- "6",
442
- "6"
443
- ],
444
- [
445
- "6",
446
- "7"
447
- ],
448
- [
449
- "6",
450
- "8"
451
- ],
452
- [
453
- "6",
454
- "9"
455
- ],
456
- [
457
- "7",
458
- "0"
459
- ],
460
- [
461
- "7",
462
- "1"
463
- ],
464
- [
465
- "7",
466
- "2"
467
- ],
468
- [
469
- "7",
470
- "3"
471
- ],
472
- [
473
- "7",
474
- "4"
475
- ],
476
- [
477
- "7",
478
- "5"
479
- ],
480
- [
481
- "7",
482
- "6"
483
- ],
484
- [
485
- "7",
486
- "7"
487
- ],
488
- [
489
- "7",
490
- "8"
491
- ],
492
- [
493
- "7",
494
- "9"
495
- ],
496
- [
497
- "8",
498
- "0"
499
- ],
500
- [
501
- "8",
502
- "1"
503
- ],
504
- [
505
- "8",
506
- "2"
507
- ],
508
- [
509
- "8",
510
- "3"
511
- ],
512
- [
513
- "8",
514
- "4"
515
- ],
516
- [
517
- "8",
518
- "5"
519
- ],
520
- [
521
- "8",
522
- "6"
523
- ],
524
- [
525
- "8",
526
- "7"
527
- ],
528
- [
529
- "8",
530
- "8"
531
- ],
532
- [
533
- "8",
534
- "9"
535
- ],
536
- [
537
- "9",
538
- "0"
539
- ],
540
- [
541
- "9",
542
- "1"
543
- ],
544
- [
545
- "9",
546
- "2"
547
- ],
548
- [
549
- "9",
550
- "3"
551
- ],
552
- [
553
- "9",
554
- "4"
555
- ],
556
- [
557
- "9",
558
- "5"
559
- ],
560
- [
561
- "9",
562
- "6"
563
- ],
564
- [
565
- "9",
566
- "7"
567
- ],
568
- [
569
- "9",
570
- "8"
571
- ],
572
- [
573
- "9",
574
- "9"
575
- ]
576
- ]
577
  }
578
  }
 
65
  "rstrip": false,
66
  "normalized": false,
67
  "special": true
68
+ },
69
+ {
70
+ "id": 7,
71
+ "content": "11",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": true,
76
+ "special": false
77
+ },
78
+ {
79
+ "id": 8,
80
+ "content": "0",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": true,
85
+ "special": false
86
+ },
87
+ {
88
+ "id": 9,
89
+ "content": "61",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": true,
94
+ "special": false
95
+ },
96
+ {
97
+ "id": 10,
98
+ "content": "72",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": true,
103
+ "special": false
104
+ },
105
+ {
106
+ "id": 11,
107
+ "content": "3",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": true,
112
+ "special": false
113
+ },
114
+ {
115
+ "id": 12,
116
+ "content": "27",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": true,
121
+ "special": false
122
+ },
123
+ {
124
+ "id": 13,
125
+ "content": "5",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": true,
130
+ "special": false
131
+ },
132
+ {
133
+ "id": 14,
134
+ "content": "18",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": true,
139
+ "special": false
140
+ },
141
+ {
142
+ "id": 15,
143
+ "content": "90",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": true,
148
+ "special": false
149
+ },
150
+ {
151
+ "id": 16,
152
+ "content": "21",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": true,
157
+ "special": false
158
+ },
159
+ {
160
+ "id": 17,
161
+ "content": "17",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": true,
166
+ "special": false
167
+ },
168
+ {
169
+ "id": 18,
170
+ "content": "28",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": true,
175
+ "special": false
176
+ },
177
+ {
178
+ "id": 19,
179
+ "content": "42",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": true,
184
+ "special": false
185
+ },
186
+ {
187
+ "id": 20,
188
+ "content": "58",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": true,
193
+ "special": false
194
+ },
195
+ {
196
+ "id": 21,
197
+ "content": "9",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": true,
202
+ "special": false
203
+ },
204
+ {
205
+ "id": 22,
206
+ "content": "36",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": true,
211
+ "special": false
212
+ },
213
+ {
214
+ "id": 23,
215
+ "content": "76",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": true,
220
+ "special": false
221
+ },
222
+ {
223
+ "id": 24,
224
+ "content": "38",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": true,
229
+ "special": false
230
+ },
231
+ {
232
+ "id": 25,
233
+ "content": "83",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": true,
238
+ "special": false
239
+ },
240
+ {
241
+ "id": 26,
242
+ "content": "89",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": true,
247
+ "special": false
248
+ },
249
+ {
250
+ "id": 27,
251
+ "content": "2",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": true,
256
+ "special": false
257
+ },
258
+ {
259
+ "id": 28,
260
+ "content": "10",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": true,
265
+ "special": false
266
+ },
267
+ {
268
+ "id": 29,
269
+ "content": "81",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": true,
274
+ "special": false
275
+ },
276
+ {
277
+ "id": 30,
278
+ "content": "35",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": true,
283
+ "special": false
284
+ },
285
+ {
286
+ "id": 31,
287
+ "content": "63",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": true,
292
+ "special": false
293
+ },
294
+ {
295
+ "id": 32,
296
+ "content": "94",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": true,
301
+ "special": false
302
+ },
303
+ {
304
+ "id": 33,
305
+ "content": "54",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": true,
310
+ "special": false
311
+ },
312
+ {
313
+ "id": 34,
314
+ "content": "87",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": true,
319
+ "special": false
320
+ },
321
+ {
322
+ "id": 35,
323
+ "content": "50",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": true,
328
+ "special": false
329
+ },
330
+ {
331
+ "id": 36,
332
+ "content": "99",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": true,
337
+ "special": false
338
+ },
339
+ {
340
+ "id": 37,
341
+ "content": "79",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": true,
346
+ "special": false
347
+ },
348
+ {
349
+ "id": 38,
350
+ "content": "16",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": true,
355
+ "special": false
356
+ },
357
+ {
358
+ "id": 39,
359
+ "content": "57",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": true,
364
+ "special": false
365
+ },
366
+ {
367
+ "id": 40,
368
+ "content": "26",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": true,
373
+ "special": false
374
+ },
375
+ {
376
+ "id": 41,
377
+ "content": "49",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": true,
382
+ "special": false
383
+ },
384
+ {
385
+ "id": 42,
386
+ "content": "68",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": true,
391
+ "special": false
392
+ },
393
+ {
394
+ "id": 43,
395
+ "content": "69",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": true,
400
+ "special": false
401
+ },
402
+ {
403
+ "id": 44,
404
+ "content": "85",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": true,
409
+ "special": false
410
+ },
411
+ {
412
+ "id": 45,
413
+ "content": "39",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": true,
418
+ "special": false
419
+ },
420
+ {
421
+ "id": 46,
422
+ "content": "45",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": true,
427
+ "special": false
428
+ },
429
+ {
430
+ "id": 47,
431
+ "content": "14",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": true,
436
+ "special": false
437
+ },
438
+ {
439
+ "id": 48,
440
+ "content": "59",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": true,
445
+ "special": false
446
+ },
447
+ {
448
+ "id": 49,
449
+ "content": "97",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": true,
454
+ "special": false
455
+ },
456
+ {
457
+ "id": 50,
458
+ "content": "62",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": true,
463
+ "special": false
464
+ },
465
+ {
466
+ "id": 51,
467
+ "content": "53",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": true,
472
+ "special": false
473
+ },
474
+ {
475
+ "id": 52,
476
+ "content": "15",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": true,
481
+ "special": false
482
+ },
483
+ {
484
+ "id": 53,
485
+ "content": "19",
486
+ "single_word": false,
487
+ "lstrip": false,
488
+ "rstrip": false,
489
+ "normalized": true,
490
+ "special": false
491
+ },
492
+ {
493
+ "id": 54,
494
+ "content": "37",
495
+ "single_word": false,
496
+ "lstrip": false,
497
+ "rstrip": false,
498
+ "normalized": true,
499
+ "special": false
500
+ },
501
+ {
502
+ "id": 55,
503
+ "content": "77",
504
+ "single_word": false,
505
+ "lstrip": false,
506
+ "rstrip": false,
507
+ "normalized": true,
508
+ "special": false
509
+ },
510
+ {
511
+ "id": 56,
512
+ "content": "95",
513
+ "single_word": false,
514
+ "lstrip": false,
515
+ "rstrip": false,
516
+ "normalized": true,
517
+ "special": false
518
+ },
519
+ {
520
+ "id": 57,
521
+ "content": "6",
522
+ "single_word": false,
523
+ "lstrip": false,
524
+ "rstrip": false,
525
+ "normalized": true,
526
+ "special": false
527
+ },
528
+ {
529
+ "id": 58,
530
+ "content": "78",
531
+ "single_word": false,
532
+ "lstrip": false,
533
+ "rstrip": false,
534
+ "normalized": true,
535
+ "special": false
536
+ },
537
+ {
538
+ "id": 59,
539
+ "content": "8",
540
+ "single_word": false,
541
+ "lstrip": false,
542
+ "rstrip": false,
543
+ "normalized": true,
544
+ "special": false
545
+ },
546
+ {
547
+ "id": 60,
548
+ "content": "24",
549
+ "single_word": false,
550
+ "lstrip": false,
551
+ "rstrip": false,
552
+ "normalized": true,
553
+ "special": false
554
+ },
555
+ {
556
+ "id": 61,
557
+ "content": "65",
558
+ "single_word": false,
559
+ "lstrip": false,
560
+ "rstrip": false,
561
+ "normalized": true,
562
+ "special": false
563
+ },
564
+ {
565
+ "id": 62,
566
+ "content": "67",
567
+ "single_word": false,
568
+ "lstrip": false,
569
+ "rstrip": false,
570
+ "normalized": true,
571
+ "special": false
572
+ },
573
+ {
574
+ "id": 63,
575
+ "content": "51",
576
+ "single_word": false,
577
+ "lstrip": false,
578
+ "rstrip": false,
579
+ "normalized": true,
580
+ "special": false
581
+ },
582
+ {
583
+ "id": 64,
584
+ "content": "75",
585
+ "single_word": false,
586
+ "lstrip": false,
587
+ "rstrip": false,
588
+ "normalized": true,
589
+ "special": false
590
+ },
591
+ {
592
+ "id": 65,
593
+ "content": "12",
594
+ "single_word": false,
595
+ "lstrip": false,
596
+ "rstrip": false,
597
+ "normalized": true,
598
+ "special": false
599
+ },
600
+ {
601
+ "id": 66,
602
+ "content": "47",
603
+ "single_word": false,
604
+ "lstrip": false,
605
+ "rstrip": false,
606
+ "normalized": true,
607
+ "special": false
608
+ },
609
+ {
610
+ "id": 67,
611
+ "content": "86",
612
+ "single_word": false,
613
+ "lstrip": false,
614
+ "rstrip": false,
615
+ "normalized": true,
616
+ "special": false
617
+ },
618
+ {
619
+ "id": 68,
620
+ "content": "7",
621
+ "single_word": false,
622
+ "lstrip": false,
623
+ "rstrip": false,
624
+ "normalized": true,
625
+ "special": false
626
+ },
627
+ {
628
+ "id": 69,
629
+ "content": "60",
630
+ "single_word": false,
631
+ "lstrip": false,
632
+ "rstrip": false,
633
+ "normalized": true,
634
+ "special": false
635
+ },
636
+ {
637
+ "id": 70,
638
+ "content": "23",
639
+ "single_word": false,
640
+ "lstrip": false,
641
+ "rstrip": false,
642
+ "normalized": true,
643
+ "special": false
644
+ },
645
+ {
646
+ "id": 71,
647
+ "content": "48",
648
+ "single_word": false,
649
+ "lstrip": false,
650
+ "rstrip": false,
651
+ "normalized": true,
652
+ "special": false
653
+ },
654
+ {
655
+ "id": 72,
656
+ "content": "30",
657
+ "single_word": false,
658
+ "lstrip": false,
659
+ "rstrip": false,
660
+ "normalized": true,
661
+ "special": false
662
+ },
663
+ {
664
+ "id": 73,
665
+ "content": "73",
666
+ "single_word": false,
667
+ "lstrip": false,
668
+ "rstrip": false,
669
+ "normalized": true,
670
+ "special": false
671
+ },
672
+ {
673
+ "id": 74,
674
+ "content": "34",
675
+ "single_word": false,
676
+ "lstrip": false,
677
+ "rstrip": false,
678
+ "normalized": true,
679
+ "special": false
680
+ },
681
+ {
682
+ "id": 75,
683
+ "content": "13",
684
+ "single_word": false,
685
+ "lstrip": false,
686
+ "rstrip": false,
687
+ "normalized": true,
688
+ "special": false
689
+ },
690
+ {
691
+ "id": 76,
692
+ "content": "52",
693
+ "single_word": false,
694
+ "lstrip": false,
695
+ "rstrip": false,
696
+ "normalized": true,
697
+ "special": false
698
+ },
699
+ {
700
+ "id": 77,
701
+ "content": "40",
702
+ "single_word": false,
703
+ "lstrip": false,
704
+ "rstrip": false,
705
+ "normalized": true,
706
+ "special": false
707
+ },
708
+ {
709
+ "id": 78,
710
+ "content": "56",
711
+ "single_word": false,
712
+ "lstrip": false,
713
+ "rstrip": false,
714
+ "normalized": true,
715
+ "special": false
716
+ },
717
+ {
718
+ "id": 79,
719
+ "content": "91",
720
+ "single_word": false,
721
+ "lstrip": false,
722
+ "rstrip": false,
723
+ "normalized": true,
724
+ "special": false
725
+ },
726
+ {
727
+ "id": 80,
728
+ "content": "71",
729
+ "single_word": false,
730
+ "lstrip": false,
731
+ "rstrip": false,
732
+ "normalized": true,
733
+ "special": false
734
+ },
735
+ {
736
+ "id": 81,
737
+ "content": "46",
738
+ "single_word": false,
739
+ "lstrip": false,
740
+ "rstrip": false,
741
+ "normalized": true,
742
+ "special": false
743
+ },
744
+ {
745
+ "id": 82,
746
+ "content": "92",
747
+ "single_word": false,
748
+ "lstrip": false,
749
+ "rstrip": false,
750
+ "normalized": true,
751
+ "special": false
752
+ },
753
+ {
754
+ "id": 83,
755
+ "content": "4",
756
+ "single_word": false,
757
+ "lstrip": false,
758
+ "rstrip": false,
759
+ "normalized": true,
760
+ "special": false
761
+ },
762
+ {
763
+ "id": 84,
764
+ "content": "32",
765
+ "single_word": false,
766
+ "lstrip": false,
767
+ "rstrip": false,
768
+ "normalized": true,
769
+ "special": false
770
+ },
771
+ {
772
+ "id": 85,
773
+ "content": "20",
774
+ "single_word": false,
775
+ "lstrip": false,
776
+ "rstrip": false,
777
+ "normalized": true,
778
+ "special": false
779
+ },
780
+ {
781
+ "id": 86,
782
+ "content": "25",
783
+ "single_word": false,
784
+ "lstrip": false,
785
+ "rstrip": false,
786
+ "normalized": true,
787
+ "special": false
788
+ },
789
+ {
790
+ "id": 87,
791
+ "content": "80",
792
+ "single_word": false,
793
+ "lstrip": false,
794
+ "rstrip": false,
795
+ "normalized": true,
796
+ "special": false
797
+ },
798
+ {
799
+ "id": 88,
800
+ "content": "22",
801
+ "single_word": false,
802
+ "lstrip": false,
803
+ "rstrip": false,
804
+ "normalized": true,
805
+ "special": false
806
+ },
807
+ {
808
+ "id": 89,
809
+ "content": "66",
810
+ "single_word": false,
811
+ "lstrip": false,
812
+ "rstrip": false,
813
+ "normalized": true,
814
+ "special": false
815
+ },
816
+ {
817
+ "id": 90,
818
+ "content": "1",
819
+ "single_word": false,
820
+ "lstrip": false,
821
+ "rstrip": false,
822
+ "normalized": true,
823
+ "special": false
824
+ },
825
+ {
826
+ "id": 91,
827
+ "content": "70",
828
+ "single_word": false,
829
+ "lstrip": false,
830
+ "rstrip": false,
831
+ "normalized": true,
832
+ "special": false
833
+ },
834
+ {
835
+ "id": 92,
836
+ "content": "88",
837
+ "single_word": false,
838
+ "lstrip": false,
839
+ "rstrip": false,
840
+ "normalized": true,
841
+ "special": false
842
+ },
843
+ {
844
+ "id": 93,
845
+ "content": "96",
846
+ "single_word": false,
847
+ "lstrip": false,
848
+ "rstrip": false,
849
+ "normalized": true,
850
+ "special": false
851
+ },
852
+ {
853
+ "id": 94,
854
+ "content": "41",
855
+ "single_word": false,
856
+ "lstrip": false,
857
+ "rstrip": false,
858
+ "normalized": true,
859
+ "special": false
860
+ },
861
+ {
862
+ "id": 95,
863
+ "content": "93",
864
+ "single_word": false,
865
+ "lstrip": false,
866
+ "rstrip": false,
867
+ "normalized": true,
868
+ "special": false
869
+ },
870
+ {
871
+ "id": 96,
872
+ "content": "84",
873
+ "single_word": false,
874
+ "lstrip": false,
875
+ "rstrip": false,
876
+ "normalized": true,
877
+ "special": false
878
+ },
879
+ {
880
+ "id": 97,
881
+ "content": "44",
882
+ "single_word": false,
883
+ "lstrip": false,
884
+ "rstrip": false,
885
+ "normalized": true,
886
+ "special": false
887
+ },
888
+ {
889
+ "id": 98,
890
+ "content": "82",
891
+ "single_word": false,
892
+ "lstrip": false,
893
+ "rstrip": false,
894
+ "normalized": true,
895
+ "special": false
896
+ },
897
+ {
898
+ "id": 99,
899
+ "content": "43",
900
+ "single_word": false,
901
+ "lstrip": false,
902
+ "rstrip": false,
903
+ "normalized": true,
904
+ "special": false
905
  }
906
  ],
907
  "normalizer": null,
 
920
  "type": "ByteLevel",
921
  "add_prefix_space": false,
922
  "trim_offsets": true,
923
+ "use_regex": false
924
  }
925
  ]
926
  },
 
947
  "<pad>": 3,
948
  "mod": 4,
949
  "=": 5,
950
+ " ": 6
951
+ },
952
+ "merges": []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
953
  }
954
  }
tokenizer_config.json CHANGED
@@ -55,6 +55,750 @@
55
  "rstrip": false,
56
  "single_word": false,
57
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
58
  }
59
  },
60
  "additional_special_tokens": [
 
55
  "rstrip": false,
56
  "single_word": false,
57
  "special": true
58
+ },
59
+ "7": {
60
+ "content": "11",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "8": {
68
+ "content": "0",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "9": {
76
+ "content": "61",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "10": {
84
+ "content": "72",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "11": {
92
+ "content": "3",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "12": {
100
+ "content": "27",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "13": {
108
+ "content": "5",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "14": {
116
+ "content": "18",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "15": {
124
+ "content": "90",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "16": {
132
+ "content": "21",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "17": {
140
+ "content": "17",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "18": {
148
+ "content": "28",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "19": {
156
+ "content": "42",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "20": {
164
+ "content": "58",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "21": {
172
+ "content": "9",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "22": {
180
+ "content": "36",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "23": {
188
+ "content": "76",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "24": {
196
+ "content": "38",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "25": {
204
+ "content": "83",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "26": {
212
+ "content": "89",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "27": {
220
+ "content": "2",
221
+ "lstrip": false,
222
+ "normalized": true,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": false
226
+ },
227
+ "28": {
228
+ "content": "10",
229
+ "lstrip": false,
230
+ "normalized": true,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": false
234
+ },
235
+ "29": {
236
+ "content": "81",
237
+ "lstrip": false,
238
+ "normalized": true,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": false
242
+ },
243
+ "30": {
244
+ "content": "35",
245
+ "lstrip": false,
246
+ "normalized": true,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": false
250
+ },
251
+ "31": {
252
+ "content": "63",
253
+ "lstrip": false,
254
+ "normalized": true,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": false
258
+ },
259
+ "32": {
260
+ "content": "94",
261
+ "lstrip": false,
262
+ "normalized": true,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": false
266
+ },
267
+ "33": {
268
+ "content": "54",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "34": {
276
+ "content": "87",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "35": {
284
+ "content": "50",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "36": {
292
+ "content": "99",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "37": {
300
+ "content": "79",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "38": {
308
+ "content": "16",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "39": {
316
+ "content": "57",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "40": {
324
+ "content": "26",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "41": {
332
+ "content": "49",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "42": {
340
+ "content": "68",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "43": {
348
+ "content": "69",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "44": {
356
+ "content": "85",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "45": {
364
+ "content": "39",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "46": {
372
+ "content": "45",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "47": {
380
+ "content": "14",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "48": {
388
+ "content": "59",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "49": {
396
+ "content": "97",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50": {
404
+ "content": "62",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "51": {
412
+ "content": "53",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "52": {
420
+ "content": "15",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "53": {
428
+ "content": "19",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "54": {
436
+ "content": "37",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "55": {
444
+ "content": "77",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "56": {
452
+ "content": "95",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "57": {
460
+ "content": "6",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "58": {
468
+ "content": "78",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "59": {
476
+ "content": "8",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "60": {
484
+ "content": "24",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "61": {
492
+ "content": "65",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "62": {
500
+ "content": "67",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "63": {
508
+ "content": "51",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "64": {
516
+ "content": "75",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "65": {
524
+ "content": "12",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "66": {
532
+ "content": "47",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "67": {
540
+ "content": "86",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "68": {
548
+ "content": "7",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "69": {
556
+ "content": "60",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "70": {
564
+ "content": "23",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "71": {
572
+ "content": "48",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "72": {
580
+ "content": "30",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "73": {
588
+ "content": "73",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "74": {
596
+ "content": "34",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "75": {
604
+ "content": "13",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "76": {
612
+ "content": "52",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "77": {
620
+ "content": "40",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "78": {
628
+ "content": "56",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "79": {
636
+ "content": "91",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "80": {
644
+ "content": "71",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "81": {
652
+ "content": "46",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "82": {
660
+ "content": "92",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "83": {
668
+ "content": "4",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "84": {
676
+ "content": "32",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "85": {
684
+ "content": "20",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "86": {
692
+ "content": "25",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "87": {
700
+ "content": "80",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "88": {
708
+ "content": "22",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "89": {
716
+ "content": "66",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "90": {
724
+ "content": "1",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "91": {
732
+ "content": "70",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "92": {
740
+ "content": "88",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "93": {
748
+ "content": "96",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "94": {
756
+ "content": "41",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "95": {
764
+ "content": "93",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "96": {
772
+ "content": "84",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "97": {
780
+ "content": "44",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "98": {
788
+ "content": "82",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "99": {
796
+ "content": "43",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
  }
803
  },
804
  "additional_special_tokens": [
vocab.json CHANGED
@@ -1,109 +1,109 @@
1
  {
2
- "17": 24,
3
- "43": 50,
4
- "16": 23,
5
- "57": 64,
6
- "9": 16,
7
- "31": 38,
 
 
 
 
 
8
  "</s>": 2,
9
- "44": 51,
10
- "26": 33,
11
- "56": 63,
12
- "21": 28,
13
- "66": 73,
14
- "48": 55,
15
- "5": 12,
16
- "=": 5,
17
- "3": 10,
18
- "94": 101,
19
- "46": 53,
20
- "71": 78,
21
- "81": 88,
22
- "61": 68,
23
- "42": 49,
24
- "4": 11,
25
- "41": 48,
26
- "65": 72,
27
- "62": 69,
28
- "<unk>": 0,
29
- "<s>": 1,
30
- "11": 18,
31
- "0": 7,
32
- "36": 43,
33
- "73": 80,
34
- "30": 37,
35
- "40": 47,
36
- "mod": 4,
37
- "22": 29,
38
- "72": 79,
39
- "87": 94,
40
- "88": 95,
41
- "76": 83,
42
- "35": 42,
43
- "99": 106,
44
- "7": 14,
45
- "34": 41,
46
- "58": 65,
47
- "23": 30,
48
- "64": 71,
49
- "25": 32,
50
- "60": 67,
51
  " ": 6,
52
- "14": 21,
53
- "45": 52,
54
- "32": 39,
55
- "1": 8,
56
- "12": 19,
57
- "50": 57,
58
- "47": 54,
59
- "67": 74,
60
- "74": 81,
61
- "18": 25,
62
- "49": 56,
63
- "85": 92,
64
- "90": 97,
65
- "2": 9,
66
- "6": 13,
67
- "15": 22,
68
- "82": 89,
69
- "27": 34,
70
- "69": 76,
71
- "79": 86,
72
- "39": 46,
73
- "97": 104,
74
- "53": 60,
75
- "8": 15,
76
- "33": 40,
77
- "13": 20,
78
- "52": 59,
79
- "96": 103,
80
- "10": 17,
81
- "37": 44,
82
- "93": 100,
83
- "89": 96,
84
- "<pad>": 3,
85
  "80": 87,
86
- "24": 31,
87
- "28": 35,
88
- "68": 75,
89
- "38": 45,
90
- "55": 62,
91
- "84": 91,
92
- "63": 70,
93
- "19": 26,
94
- "86": 93,
95
- "91": 98,
96
- "51": 58,
97
- "20": 27,
98
- "54": 61,
99
- "75": 82,
100
- "29": 36,
101
- "77": 84,
102
- "59": 66,
103
- "98": 105,
104
- "83": 90,
105
- "95": 102,
106
- "78": 85,
107
- "70": 77,
108
- "92": 99
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
109
  }
 
1
  {
2
+ "12": 65,
3
+ "94": 32,
4
+ "55": 0,
5
+ "35": 30,
6
+ "97": 49,
7
+ "1": 90,
8
+ "88": 92,
9
+ "96": 93,
10
+ "30": 72,
11
+ "86": 67,
12
+ "8": 59,
13
  "</s>": 2,
14
+ "11": 7,
15
+ "74": 5,
16
+ "89": 26,
17
+ "0": 8,
18
+ "92": 82,
19
+ "27": 12,
20
+ "54": 33,
21
+ "64": 4,
22
+ "59": 48,
23
+ "31": 2,
24
+ "5": 13,
25
+ "93": 95,
26
+ "90": 15,
27
+ "91": 79,
28
+ "2": 27,
29
+ "75": 64,
30
+ "62": 50,
31
+ "82": 98,
32
+ "21": 16,
33
+ "63": 31,
34
+ "81": 29,
35
+ "9": 21,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  " ": 6,
37
+ "58": 20,
38
+ "25": 86,
39
+ "41": 94,
40
+ "99": 36,
41
+ "71": 80,
42
+ "26": 40,
43
+ "79": 37,
44
+ "56": 78,
45
+ "67": 62,
46
+ "37": 54,
47
+ "10": 28,
48
+ "mod": 4,
49
+ "48": 71,
50
+ "57": 39,
51
+ "13": 75,
52
+ "33": 1,
53
+ "7": 68,
54
+ "85": 44,
55
+ "42": 19,
56
+ "98": 6,
57
+ "70": 91,
58
+ "49": 41,
59
+ "36": 22,
60
+ "83": 25,
61
+ "<unk>": 0,
62
+ "95": 56,
 
 
 
 
 
 
 
63
  "80": 87,
64
+ "39": 45,
65
+ "6": 57,
66
+ "<pad>": 3,
67
+ "29": 3,
68
+ "45": 46,
69
+ "22": 88,
70
+ "14": 47,
71
+ "34": 74,
72
+ "15": 52,
73
+ "17": 17,
74
+ "23": 70,
75
+ "38": 24,
76
+ "60": 69,
77
+ "16": 38,
78
+ "61": 9,
79
+ "87": 34,
80
+ "32": 84,
81
+ "28": 18,
82
+ "4": 83,
83
+ "18": 14,
84
+ "24": 60,
85
+ "69": 43,
86
+ "43": 99,
87
+ "73": 73,
88
+ "72": 10,
89
+ "44": 97,
90
+ "68": 42,
91
+ "40": 77,
92
+ "78": 58,
93
+ "=": 5,
94
+ "77": 55,
95
+ "47": 66,
96
+ "3": 11,
97
+ "52": 76,
98
+ "46": 81,
99
+ "20": 85,
100
+ "65": 61,
101
+ "84": 96,
102
+ "51": 63,
103
+ "76": 23,
104
+ "53": 51,
105
+ "50": 35,
106
+ "19": 53,
107
+ "<s>": 1,
108
+ "66": 89
109
  }