Ehsanjahanbakhsh commited on
Commit
2b10b82
1 Parent(s): eb925c3

Better Tokenization

Browse files

Created a better tokenizer from sentencepiece model. please test it.

added_tokens.json CHANGED
@@ -1,103 +1,2 @@
1
  {
2
- "<extra_id_0>": 256099,
3
- "<extra_id_10>": 256089,
4
- "<extra_id_11>": 256088,
5
- "<extra_id_12>": 256087,
6
- "<extra_id_13>": 256086,
7
- "<extra_id_14>": 256085,
8
- "<extra_id_15>": 256084,
9
- "<extra_id_16>": 256083,
10
- "<extra_id_17>": 256082,
11
- "<extra_id_18>": 256081,
12
- "<extra_id_19>": 256080,
13
- "<extra_id_1>": 256098,
14
- "<extra_id_20>": 256079,
15
- "<extra_id_21>": 256078,
16
- "<extra_id_22>": 256077,
17
- "<extra_id_23>": 256076,
18
- "<extra_id_24>": 256075,
19
- "<extra_id_25>": 256074,
20
- "<extra_id_26>": 256073,
21
- "<extra_id_27>": 256072,
22
- "<extra_id_28>": 256071,
23
- "<extra_id_29>": 256070,
24
- "<extra_id_2>": 256097,
25
- "<extra_id_30>": 256069,
26
- "<extra_id_31>": 256068,
27
- "<extra_id_32>": 256067,
28
- "<extra_id_33>": 256066,
29
- "<extra_id_34>": 256065,
30
- "<extra_id_35>": 256064,
31
- "<extra_id_36>": 256063,
32
- "<extra_id_37>": 256062,
33
- "<extra_id_38>": 256061,
34
- "<extra_id_39>": 256060,
35
- "<extra_id_3>": 256096,
36
- "<extra_id_40>": 256059,
37
- "<extra_id_41>": 256058,
38
- "<extra_id_42>": 256057,
39
- "<extra_id_43>": 256056,
40
- "<extra_id_44>": 256055,
41
- "<extra_id_45>": 256054,
42
- "<extra_id_46>": 256053,
43
- "<extra_id_47>": 256052,
44
- "<extra_id_48>": 256051,
45
- "<extra_id_49>": 256050,
46
- "<extra_id_4>": 256095,
47
- "<extra_id_50>": 256049,
48
- "<extra_id_51>": 256048,
49
- "<extra_id_52>": 256047,
50
- "<extra_id_53>": 256046,
51
- "<extra_id_54>": 256045,
52
- "<extra_id_55>": 256044,
53
- "<extra_id_56>": 256043,
54
- "<extra_id_57>": 256042,
55
- "<extra_id_58>": 256041,
56
- "<extra_id_59>": 256040,
57
- "<extra_id_5>": 256094,
58
- "<extra_id_60>": 256039,
59
- "<extra_id_61>": 256038,
60
- "<extra_id_62>": 256037,
61
- "<extra_id_63>": 256036,
62
- "<extra_id_64>": 256035,
63
- "<extra_id_65>": 256034,
64
- "<extra_id_66>": 256033,
65
- "<extra_id_67>": 256032,
66
- "<extra_id_68>": 256031,
67
- "<extra_id_69>": 256030,
68
- "<extra_id_6>": 256093,
69
- "<extra_id_70>": 256029,
70
- "<extra_id_71>": 256028,
71
- "<extra_id_72>": 256027,
72
- "<extra_id_73>": 256026,
73
- "<extra_id_74>": 256025,
74
- "<extra_id_75>": 256024,
75
- "<extra_id_76>": 256023,
76
- "<extra_id_77>": 256022,
77
- "<extra_id_78>": 256021,
78
- "<extra_id_79>": 256020,
79
- "<extra_id_7>": 256092,
80
- "<extra_id_80>": 256019,
81
- "<extra_id_81>": 256018,
82
- "<extra_id_82>": 256017,
83
- "<extra_id_83>": 256016,
84
- "<extra_id_84>": 256015,
85
- "<extra_id_85>": 256014,
86
- "<extra_id_86>": 256013,
87
- "<extra_id_87>": 256012,
88
- "<extra_id_88>": 256011,
89
- "<extra_id_89>": 256010,
90
- "<extra_id_8>": 256091,
91
- "<extra_id_90>": 256009,
92
- "<extra_id_91>": 256008,
93
- "<extra_id_92>": 256007,
94
- "<extra_id_93>": 256006,
95
- "<extra_id_94>": 256005,
96
- "<extra_id_95>": 256004,
97
- "<extra_id_96>": 256003,
98
- "<extra_id_97>": 256002,
99
- "<extra_id_98>": 256001,
100
- "<extra_id_99>": 256000,
101
- "<extra_id_9>": 256090,
102
- "<pad>": 256100
103
  }
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  }
special_tokens_map.json CHANGED
@@ -1,106 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- "<extra_id_0>",
4
- "<extra_id_1>",
5
- "<extra_id_2>",
6
- "<extra_id_3>",
7
- "<extra_id_4>",
8
- "<extra_id_5>",
9
- "<extra_id_6>",
10
- "<extra_id_7>",
11
- "<extra_id_8>",
12
- "<extra_id_9>",
13
- "<extra_id_10>",
14
- "<extra_id_11>",
15
- "<extra_id_12>",
16
- "<extra_id_13>",
17
- "<extra_id_14>",
18
- "<extra_id_15>",
19
- "<extra_id_16>",
20
- "<extra_id_17>",
21
- "<extra_id_18>",
22
- "<extra_id_19>",
23
- "<extra_id_20>",
24
- "<extra_id_21>",
25
- "<extra_id_22>",
26
- "<extra_id_23>",
27
- "<extra_id_24>",
28
- "<extra_id_25>",
29
- "<extra_id_26>",
30
- "<extra_id_27>",
31
- "<extra_id_28>",
32
- "<extra_id_29>",
33
- "<extra_id_30>",
34
- "<extra_id_31>",
35
- "<extra_id_32>",
36
- "<extra_id_33>",
37
- "<extra_id_34>",
38
- "<extra_id_35>",
39
- "<extra_id_36>",
40
- "<extra_id_37>",
41
- "<extra_id_38>",
42
- "<extra_id_39>",
43
- "<extra_id_40>",
44
- "<extra_id_41>",
45
- "<extra_id_42>",
46
- "<extra_id_43>",
47
- "<extra_id_44>",
48
- "<extra_id_45>",
49
- "<extra_id_46>",
50
- "<extra_id_47>",
51
- "<extra_id_48>",
52
- "<extra_id_49>",
53
- "<extra_id_50>",
54
- "<extra_id_51>",
55
- "<extra_id_52>",
56
- "<extra_id_53>",
57
- "<extra_id_54>",
58
- "<extra_id_55>",
59
- "<extra_id_56>",
60
- "<extra_id_57>",
61
- "<extra_id_58>",
62
- "<extra_id_59>",
63
- "<extra_id_60>",
64
- "<extra_id_61>",
65
- "<extra_id_62>",
66
- "<extra_id_63>",
67
- "<extra_id_64>",
68
- "<extra_id_65>",
69
- "<extra_id_66>",
70
- "<extra_id_67>",
71
- "<extra_id_68>",
72
- "<extra_id_69>",
73
- "<extra_id_70>",
74
- "<extra_id_71>",
75
- "<extra_id_72>",
76
- "<extra_id_73>",
77
- "<extra_id_74>",
78
- "<extra_id_75>",
79
- "<extra_id_76>",
80
- "<extra_id_77>",
81
- "<extra_id_78>",
82
- "<extra_id_79>",
83
- "<extra_id_80>",
84
- "<extra_id_81>",
85
- "<extra_id_82>",
86
- "<extra_id_83>",
87
- "<extra_id_84>",
88
- "<extra_id_85>",
89
- "<extra_id_86>",
90
- "<extra_id_87>",
91
- "<extra_id_88>",
92
- "<extra_id_89>",
93
- "<extra_id_90>",
94
- "<extra_id_91>",
95
- "<extra_id_92>",
96
- "<extra_id_93>",
97
- "<extra_id_94>",
98
- "<extra_id_95>",
99
- "<extra_id_96>",
100
- "<extra_id_97>",
101
- "<extra_id_98>",
102
- "<extra_id_99>"
103
- ],
104
  "eos_token": {
105
  "content": "</s>",
106
  "lstrip": false,
@@ -109,7 +7,7 @@
109
  "single_word": false
110
  },
111
  "pad_token": {
112
- "content": "<pad>",
113
  "lstrip": false,
114
  "normalized": false,
115
  "rstrip": false,
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "eos_token": {
3
  "content": "</s>",
4
  "lstrip": false,
 
7
  "single_word": false
8
  },
9
  "pad_token": {
10
+ "content": "<s>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ceb4f73d0ecf9131e8fbf80b7b5261c202f85b69d3b24f822bf59249b16cccc
3
- size 16634421
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2799ccc696b752ba00c34f58726bfe253a04921ceb6cfc620400f560474790b
3
+ size 16629031
tokenizer_config.json CHANGED
@@ -8,816 +8,16 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "2": {
12
- "content": "</s>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "256000": {
20
- "content": "<extra_id_99>",
21
- "lstrip": true,
22
- "normalized": false,
23
- "rstrip": true,
24
- "single_word": true,
25
- "special": true
26
- },
27
- "256001": {
28
- "content": "<extra_id_98>",
29
- "lstrip": true,
30
- "normalized": false,
31
- "rstrip": true,
32
- "single_word": true,
33
- "special": true
34
- },
35
- "256002": {
36
- "content": "<extra_id_97>",
37
- "lstrip": true,
38
- "normalized": false,
39
- "rstrip": true,
40
- "single_word": true,
41
- "special": true
42
- },
43
- "256003": {
44
- "content": "<extra_id_96>",
45
- "lstrip": true,
46
- "normalized": false,
47
- "rstrip": true,
48
- "single_word": true,
49
- "special": true
50
- },
51
- "256004": {
52
- "content": "<extra_id_95>",
53
- "lstrip": true,
54
- "normalized": false,
55
- "rstrip": true,
56
- "single_word": true,
57
- "special": true
58
- },
59
- "256005": {
60
- "content": "<extra_id_94>",
61
- "lstrip": true,
62
- "normalized": false,
63
- "rstrip": true,
64
- "single_word": true,
65
- "special": true
66
- },
67
- "256006": {
68
- "content": "<extra_id_93>",
69
- "lstrip": true,
70
- "normalized": false,
71
- "rstrip": true,
72
- "single_word": true,
73
- "special": true
74
- },
75
- "256007": {
76
- "content": "<extra_id_92>",
77
- "lstrip": true,
78
- "normalized": false,
79
- "rstrip": true,
80
- "single_word": true,
81
- "special": true
82
- },
83
- "256008": {
84
- "content": "<extra_id_91>",
85
- "lstrip": true,
86
- "normalized": false,
87
- "rstrip": true,
88
- "single_word": true,
89
- "special": true
90
- },
91
- "256009": {
92
- "content": "<extra_id_90>",
93
- "lstrip": true,
94
- "normalized": false,
95
- "rstrip": true,
96
- "single_word": true,
97
- "special": true
98
- },
99
- "256010": {
100
- "content": "<extra_id_89>",
101
- "lstrip": true,
102
- "normalized": false,
103
- "rstrip": true,
104
- "single_word": true,
105
- "special": true
106
- },
107
- "256011": {
108
- "content": "<extra_id_88>",
109
- "lstrip": true,
110
- "normalized": false,
111
- "rstrip": true,
112
- "single_word": true,
113
- "special": true
114
- },
115
- "256012": {
116
- "content": "<extra_id_87>",
117
- "lstrip": true,
118
- "normalized": false,
119
- "rstrip": true,
120
- "single_word": true,
121
- "special": true
122
- },
123
- "256013": {
124
- "content": "<extra_id_86>",
125
- "lstrip": true,
126
- "normalized": false,
127
- "rstrip": true,
128
- "single_word": true,
129
- "special": true
130
- },
131
- "256014": {
132
- "content": "<extra_id_85>",
133
- "lstrip": true,
134
- "normalized": false,
135
- "rstrip": true,
136
- "single_word": true,
137
- "special": true
138
- },
139
- "256015": {
140
- "content": "<extra_id_84>",
141
- "lstrip": true,
142
- "normalized": false,
143
- "rstrip": true,
144
- "single_word": true,
145
- "special": true
146
- },
147
- "256016": {
148
- "content": "<extra_id_83>",
149
- "lstrip": true,
150
- "normalized": false,
151
- "rstrip": true,
152
- "single_word": true,
153
- "special": true
154
- },
155
- "256017": {
156
- "content": "<extra_id_82>",
157
- "lstrip": true,
158
- "normalized": false,
159
- "rstrip": true,
160
- "single_word": true,
161
- "special": true
162
- },
163
- "256018": {
164
- "content": "<extra_id_81>",
165
- "lstrip": true,
166
- "normalized": false,
167
- "rstrip": true,
168
- "single_word": true,
169
- "special": true
170
- },
171
- "256019": {
172
- "content": "<extra_id_80>",
173
- "lstrip": true,
174
- "normalized": false,
175
- "rstrip": true,
176
- "single_word": true,
177
- "special": true
178
- },
179
- "256020": {
180
- "content": "<extra_id_79>",
181
- "lstrip": true,
182
- "normalized": false,
183
- "rstrip": true,
184
- "single_word": true,
185
- "special": true
186
- },
187
- "256021": {
188
- "content": "<extra_id_78>",
189
- "lstrip": true,
190
- "normalized": false,
191
- "rstrip": true,
192
- "single_word": true,
193
- "special": true
194
- },
195
- "256022": {
196
- "content": "<extra_id_77>",
197
- "lstrip": true,
198
- "normalized": false,
199
- "rstrip": true,
200
- "single_word": true,
201
- "special": true
202
- },
203
- "256023": {
204
- "content": "<extra_id_76>",
205
- "lstrip": true,
206
- "normalized": false,
207
- "rstrip": true,
208
- "single_word": true,
209
- "special": true
210
- },
211
- "256024": {
212
- "content": "<extra_id_75>",
213
- "lstrip": true,
214
- "normalized": false,
215
- "rstrip": true,
216
- "single_word": true,
217
- "special": true
218
- },
219
- "256025": {
220
- "content": "<extra_id_74>",
221
- "lstrip": true,
222
- "normalized": false,
223
- "rstrip": true,
224
- "single_word": true,
225
- "special": true
226
- },
227
- "256026": {
228
- "content": "<extra_id_73>",
229
- "lstrip": true,
230
- "normalized": false,
231
- "rstrip": true,
232
- "single_word": true,
233
- "special": true
234
- },
235
- "256027": {
236
- "content": "<extra_id_72>",
237
- "lstrip": true,
238
- "normalized": false,
239
- "rstrip": true,
240
- "single_word": true,
241
- "special": true
242
- },
243
- "256028": {
244
- "content": "<extra_id_71>",
245
- "lstrip": true,
246
- "normalized": false,
247
- "rstrip": true,
248
- "single_word": true,
249
- "special": true
250
- },
251
- "256029": {
252
- "content": "<extra_id_70>",
253
- "lstrip": true,
254
- "normalized": false,
255
- "rstrip": true,
256
- "single_word": true,
257
- "special": true
258
- },
259
- "256030": {
260
- "content": "<extra_id_69>",
261
- "lstrip": true,
262
- "normalized": false,
263
- "rstrip": true,
264
- "single_word": true,
265
- "special": true
266
- },
267
- "256031": {
268
- "content": "<extra_id_68>",
269
- "lstrip": true,
270
- "normalized": false,
271
- "rstrip": true,
272
- "single_word": true,
273
- "special": true
274
- },
275
- "256032": {
276
- "content": "<extra_id_67>",
277
- "lstrip": true,
278
- "normalized": false,
279
- "rstrip": true,
280
- "single_word": true,
281
- "special": true
282
- },
283
- "256033": {
284
- "content": "<extra_id_66>",
285
- "lstrip": true,
286
- "normalized": false,
287
- "rstrip": true,
288
- "single_word": true,
289
- "special": true
290
- },
291
- "256034": {
292
- "content": "<extra_id_65>",
293
- "lstrip": true,
294
- "normalized": false,
295
- "rstrip": true,
296
- "single_word": true,
297
- "special": true
298
- },
299
- "256035": {
300
- "content": "<extra_id_64>",
301
- "lstrip": true,
302
- "normalized": false,
303
- "rstrip": true,
304
- "single_word": true,
305
- "special": true
306
- },
307
- "256036": {
308
- "content": "<extra_id_63>",
309
- "lstrip": true,
310
- "normalized": false,
311
- "rstrip": true,
312
- "single_word": true,
313
- "special": true
314
- },
315
- "256037": {
316
- "content": "<extra_id_62>",
317
- "lstrip": true,
318
- "normalized": false,
319
- "rstrip": true,
320
- "single_word": true,
321
- "special": true
322
- },
323
- "256038": {
324
- "content": "<extra_id_61>",
325
- "lstrip": true,
326
- "normalized": false,
327
- "rstrip": true,
328
- "single_word": true,
329
- "special": true
330
- },
331
- "256039": {
332
- "content": "<extra_id_60>",
333
- "lstrip": true,
334
- "normalized": false,
335
- "rstrip": true,
336
- "single_word": true,
337
- "special": true
338
- },
339
- "256040": {
340
- "content": "<extra_id_59>",
341
- "lstrip": true,
342
- "normalized": false,
343
- "rstrip": true,
344
- "single_word": true,
345
- "special": true
346
- },
347
- "256041": {
348
- "content": "<extra_id_58>",
349
- "lstrip": true,
350
- "normalized": false,
351
- "rstrip": true,
352
- "single_word": true,
353
- "special": true
354
- },
355
- "256042": {
356
- "content": "<extra_id_57>",
357
- "lstrip": true,
358
- "normalized": false,
359
- "rstrip": true,
360
- "single_word": true,
361
- "special": true
362
- },
363
- "256043": {
364
- "content": "<extra_id_56>",
365
- "lstrip": true,
366
- "normalized": false,
367
- "rstrip": true,
368
- "single_word": true,
369
- "special": true
370
- },
371
- "256044": {
372
- "content": "<extra_id_55>",
373
- "lstrip": true,
374
- "normalized": false,
375
- "rstrip": true,
376
- "single_word": true,
377
- "special": true
378
- },
379
- "256045": {
380
- "content": "<extra_id_54>",
381
- "lstrip": true,
382
- "normalized": false,
383
- "rstrip": true,
384
- "single_word": true,
385
- "special": true
386
- },
387
- "256046": {
388
- "content": "<extra_id_53>",
389
- "lstrip": true,
390
- "normalized": false,
391
- "rstrip": true,
392
- "single_word": true,
393
- "special": true
394
- },
395
- "256047": {
396
- "content": "<extra_id_52>",
397
- "lstrip": true,
398
- "normalized": false,
399
- "rstrip": true,
400
- "single_word": true,
401
- "special": true
402
- },
403
- "256048": {
404
- "content": "<extra_id_51>",
405
- "lstrip": true,
406
- "normalized": false,
407
- "rstrip": true,
408
- "single_word": true,
409
- "special": true
410
- },
411
- "256049": {
412
- "content": "<extra_id_50>",
413
- "lstrip": true,
414
- "normalized": false,
415
- "rstrip": true,
416
- "single_word": true,
417
- "special": true
418
- },
419
- "256050": {
420
- "content": "<extra_id_49>",
421
- "lstrip": true,
422
- "normalized": false,
423
- "rstrip": true,
424
- "single_word": true,
425
- "special": true
426
- },
427
- "256051": {
428
- "content": "<extra_id_48>",
429
- "lstrip": true,
430
- "normalized": false,
431
- "rstrip": true,
432
- "single_word": true,
433
- "special": true
434
- },
435
- "256052": {
436
- "content": "<extra_id_47>",
437
- "lstrip": true,
438
- "normalized": false,
439
- "rstrip": true,
440
- "single_word": true,
441
- "special": true
442
- },
443
- "256053": {
444
- "content": "<extra_id_46>",
445
- "lstrip": true,
446
- "normalized": false,
447
- "rstrip": true,
448
- "single_word": true,
449
- "special": true
450
- },
451
- "256054": {
452
- "content": "<extra_id_45>",
453
- "lstrip": true,
454
- "normalized": false,
455
- "rstrip": true,
456
- "single_word": true,
457
- "special": true
458
- },
459
- "256055": {
460
- "content": "<extra_id_44>",
461
- "lstrip": true,
462
- "normalized": false,
463
- "rstrip": true,
464
- "single_word": true,
465
- "special": true
466
- },
467
- "256056": {
468
- "content": "<extra_id_43>",
469
- "lstrip": true,
470
- "normalized": false,
471
- "rstrip": true,
472
- "single_word": true,
473
- "special": true
474
- },
475
- "256057": {
476
- "content": "<extra_id_42>",
477
- "lstrip": true,
478
- "normalized": false,
479
- "rstrip": true,
480
- "single_word": true,
481
- "special": true
482
- },
483
- "256058": {
484
- "content": "<extra_id_41>",
485
- "lstrip": true,
486
- "normalized": false,
487
- "rstrip": true,
488
- "single_word": true,
489
- "special": true
490
- },
491
- "256059": {
492
- "content": "<extra_id_40>",
493
- "lstrip": true,
494
- "normalized": false,
495
- "rstrip": true,
496
- "single_word": true,
497
- "special": true
498
- },
499
- "256060": {
500
- "content": "<extra_id_39>",
501
- "lstrip": true,
502
- "normalized": false,
503
- "rstrip": true,
504
- "single_word": true,
505
- "special": true
506
- },
507
- "256061": {
508
- "content": "<extra_id_38>",
509
- "lstrip": true,
510
- "normalized": false,
511
- "rstrip": true,
512
- "single_word": true,
513
- "special": true
514
- },
515
- "256062": {
516
- "content": "<extra_id_37>",
517
- "lstrip": true,
518
- "normalized": false,
519
- "rstrip": true,
520
- "single_word": true,
521
- "special": true
522
- },
523
- "256063": {
524
- "content": "<extra_id_36>",
525
- "lstrip": true,
526
- "normalized": false,
527
- "rstrip": true,
528
- "single_word": true,
529
- "special": true
530
- },
531
- "256064": {
532
- "content": "<extra_id_35>",
533
- "lstrip": true,
534
- "normalized": false,
535
- "rstrip": true,
536
- "single_word": true,
537
- "special": true
538
- },
539
- "256065": {
540
- "content": "<extra_id_34>",
541
- "lstrip": true,
542
- "normalized": false,
543
- "rstrip": true,
544
- "single_word": true,
545
- "special": true
546
- },
547
- "256066": {
548
- "content": "<extra_id_33>",
549
- "lstrip": true,
550
- "normalized": false,
551
- "rstrip": true,
552
- "single_word": true,
553
- "special": true
554
- },
555
- "256067": {
556
- "content": "<extra_id_32>",
557
- "lstrip": true,
558
- "normalized": false,
559
- "rstrip": true,
560
- "single_word": true,
561
- "special": true
562
- },
563
- "256068": {
564
- "content": "<extra_id_31>",
565
- "lstrip": true,
566
- "normalized": false,
567
- "rstrip": true,
568
- "single_word": true,
569
- "special": true
570
- },
571
- "256069": {
572
- "content": "<extra_id_30>",
573
- "lstrip": true,
574
- "normalized": false,
575
- "rstrip": true,
576
- "single_word": true,
577
- "special": true
578
- },
579
- "256070": {
580
- "content": "<extra_id_29>",
581
- "lstrip": true,
582
- "normalized": false,
583
- "rstrip": true,
584
- "single_word": true,
585
- "special": true
586
- },
587
- "256071": {
588
- "content": "<extra_id_28>",
589
- "lstrip": true,
590
- "normalized": false,
591
- "rstrip": true,
592
- "single_word": true,
593
- "special": true
594
- },
595
- "256072": {
596
- "content": "<extra_id_27>",
597
- "lstrip": true,
598
- "normalized": false,
599
- "rstrip": true,
600
- "single_word": true,
601
- "special": true
602
- },
603
- "256073": {
604
- "content": "<extra_id_26>",
605
- "lstrip": true,
606
- "normalized": false,
607
- "rstrip": true,
608
- "single_word": true,
609
- "special": true
610
- },
611
- "256074": {
612
- "content": "<extra_id_25>",
613
- "lstrip": true,
614
- "normalized": false,
615
- "rstrip": true,
616
- "single_word": true,
617
- "special": true
618
- },
619
- "256075": {
620
- "content": "<extra_id_24>",
621
- "lstrip": true,
622
- "normalized": false,
623
- "rstrip": true,
624
- "single_word": true,
625
- "special": true
626
- },
627
- "256076": {
628
- "content": "<extra_id_23>",
629
- "lstrip": true,
630
- "normalized": false,
631
- "rstrip": true,
632
- "single_word": true,
633
- "special": true
634
- },
635
- "256077": {
636
- "content": "<extra_id_22>",
637
- "lstrip": true,
638
- "normalized": false,
639
- "rstrip": true,
640
- "single_word": true,
641
- "special": true
642
- },
643
- "256078": {
644
- "content": "<extra_id_21>",
645
- "lstrip": true,
646
- "normalized": false,
647
- "rstrip": true,
648
- "single_word": true,
649
- "special": true
650
- },
651
- "256079": {
652
- "content": "<extra_id_20>",
653
- "lstrip": true,
654
- "normalized": false,
655
- "rstrip": true,
656
- "single_word": true,
657
- "special": true
658
- },
659
- "256080": {
660
- "content": "<extra_id_19>",
661
- "lstrip": true,
662
- "normalized": false,
663
- "rstrip": true,
664
- "single_word": true,
665
- "special": true
666
- },
667
- "256081": {
668
- "content": "<extra_id_18>",
669
- "lstrip": true,
670
- "normalized": false,
671
- "rstrip": true,
672
- "single_word": true,
673
- "special": true
674
- },
675
- "256082": {
676
- "content": "<extra_id_17>",
677
- "lstrip": true,
678
- "normalized": false,
679
- "rstrip": true,
680
- "single_word": true,
681
- "special": true
682
- },
683
- "256083": {
684
- "content": "<extra_id_16>",
685
- "lstrip": true,
686
- "normalized": false,
687
- "rstrip": true,
688
- "single_word": true,
689
- "special": true
690
- },
691
- "256084": {
692
- "content": "<extra_id_15>",
693
- "lstrip": true,
694
- "normalized": false,
695
- "rstrip": true,
696
- "single_word": true,
697
- "special": true
698
- },
699
- "256085": {
700
- "content": "<extra_id_14>",
701
- "lstrip": true,
702
- "normalized": false,
703
- "rstrip": true,
704
- "single_word": true,
705
- "special": true
706
- },
707
- "256086": {
708
- "content": "<extra_id_13>",
709
- "lstrip": true,
710
- "normalized": false,
711
- "rstrip": true,
712
- "single_word": true,
713
- "special": true
714
- },
715
- "256087": {
716
- "content": "<extra_id_12>",
717
- "lstrip": true,
718
- "normalized": false,
719
- "rstrip": true,
720
- "single_word": true,
721
- "special": true
722
- },
723
- "256088": {
724
- "content": "<extra_id_11>",
725
- "lstrip": true,
726
- "normalized": false,
727
- "rstrip": true,
728
- "single_word": true,
729
- "special": true
730
- },
731
- "256089": {
732
- "content": "<extra_id_10>",
733
- "lstrip": true,
734
- "normalized": false,
735
- "rstrip": true,
736
- "single_word": true,
737
- "special": true
738
- },
739
- "256090": {
740
- "content": "<extra_id_9>",
741
- "lstrip": true,
742
- "normalized": false,
743
- "rstrip": true,
744
- "single_word": true,
745
- "special": true
746
- },
747
- "256091": {
748
- "content": "<extra_id_8>",
749
- "lstrip": true,
750
- "normalized": false,
751
- "rstrip": true,
752
- "single_word": true,
753
- "special": true
754
- },
755
- "256092": {
756
- "content": "<extra_id_7>",
757
- "lstrip": true,
758
- "normalized": false,
759
- "rstrip": true,
760
- "single_word": true,
761
- "special": true
762
- },
763
- "256093": {
764
- "content": "<extra_id_6>",
765
- "lstrip": true,
766
- "normalized": false,
767
- "rstrip": true,
768
- "single_word": true,
769
- "special": true
770
- },
771
- "256094": {
772
- "content": "<extra_id_5>",
773
- "lstrip": true,
774
- "normalized": false,
775
- "rstrip": true,
776
- "single_word": true,
777
- "special": true
778
- },
779
- "256095": {
780
- "content": "<extra_id_4>",
781
- "lstrip": true,
782
- "normalized": false,
783
- "rstrip": true,
784
- "single_word": true,
785
- "special": true
786
- },
787
- "256096": {
788
- "content": "<extra_id_3>",
789
- "lstrip": true,
790
- "normalized": false,
791
- "rstrip": true,
792
- "single_word": true,
793
- "special": true
794
- },
795
- "256097": {
796
- "content": "<extra_id_2>",
797
- "lstrip": true,
798
- "normalized": false,
799
- "rstrip": true,
800
- "single_word": true,
801
- "special": true
802
- },
803
- "256098": {
804
- "content": "<extra_id_1>",
805
- "lstrip": true,
806
- "normalized": false,
807
- "rstrip": true,
808
- "single_word": true,
809
- "special": true
810
- },
811
- "256099": {
812
- "content": "<extra_id_0>",
813
- "lstrip": true,
814
- "normalized": false,
815
- "rstrip": true,
816
- "single_word": true,
817
- "special": true
818
- },
819
- "256100": {
820
- "content": "<pad>",
821
  "lstrip": false,
822
  "normalized": false,
823
  "rstrip": false,
@@ -825,114 +25,13 @@
825
  "special": true
826
  }
827
  },
828
- "additional_special_tokens": [
829
- "<extra_id_0>",
830
- "<extra_id_1>",
831
- "<extra_id_2>",
832
- "<extra_id_3>",
833
- "<extra_id_4>",
834
- "<extra_id_5>",
835
- "<extra_id_6>",
836
- "<extra_id_7>",
837
- "<extra_id_8>",
838
- "<extra_id_9>",
839
- "<extra_id_10>",
840
- "<extra_id_11>",
841
- "<extra_id_12>",
842
- "<extra_id_13>",
843
- "<extra_id_14>",
844
- "<extra_id_15>",
845
- "<extra_id_16>",
846
- "<extra_id_17>",
847
- "<extra_id_18>",
848
- "<extra_id_19>",
849
- "<extra_id_20>",
850
- "<extra_id_21>",
851
- "<extra_id_22>",
852
- "<extra_id_23>",
853
- "<extra_id_24>",
854
- "<extra_id_25>",
855
- "<extra_id_26>",
856
- "<extra_id_27>",
857
- "<extra_id_28>",
858
- "<extra_id_29>",
859
- "<extra_id_30>",
860
- "<extra_id_31>",
861
- "<extra_id_32>",
862
- "<extra_id_33>",
863
- "<extra_id_34>",
864
- "<extra_id_35>",
865
- "<extra_id_36>",
866
- "<extra_id_37>",
867
- "<extra_id_38>",
868
- "<extra_id_39>",
869
- "<extra_id_40>",
870
- "<extra_id_41>",
871
- "<extra_id_42>",
872
- "<extra_id_43>",
873
- "<extra_id_44>",
874
- "<extra_id_45>",
875
- "<extra_id_46>",
876
- "<extra_id_47>",
877
- "<extra_id_48>",
878
- "<extra_id_49>",
879
- "<extra_id_50>",
880
- "<extra_id_51>",
881
- "<extra_id_52>",
882
- "<extra_id_53>",
883
- "<extra_id_54>",
884
- "<extra_id_55>",
885
- "<extra_id_56>",
886
- "<extra_id_57>",
887
- "<extra_id_58>",
888
- "<extra_id_59>",
889
- "<extra_id_60>",
890
- "<extra_id_61>",
891
- "<extra_id_62>",
892
- "<extra_id_63>",
893
- "<extra_id_64>",
894
- "<extra_id_65>",
895
- "<extra_id_66>",
896
- "<extra_id_67>",
897
- "<extra_id_68>",
898
- "<extra_id_69>",
899
- "<extra_id_70>",
900
- "<extra_id_71>",
901
- "<extra_id_72>",
902
- "<extra_id_73>",
903
- "<extra_id_74>",
904
- "<extra_id_75>",
905
- "<extra_id_76>",
906
- "<extra_id_77>",
907
- "<extra_id_78>",
908
- "<extra_id_79>",
909
- "<extra_id_80>",
910
- "<extra_id_81>",
911
- "<extra_id_82>",
912
- "<extra_id_83>",
913
- "<extra_id_84>",
914
- "<extra_id_85>",
915
- "<extra_id_86>",
916
- "<extra_id_87>",
917
- "<extra_id_88>",
918
- "<extra_id_89>",
919
- "<extra_id_90>",
920
- "<extra_id_91>",
921
- "<extra_id_92>",
922
- "<extra_id_93>",
923
- "<extra_id_94>",
924
- "<extra_id_95>",
925
- "<extra_id_96>",
926
- "<extra_id_97>",
927
- "<extra_id_98>",
928
- "<extra_id_99>"
929
- ],
930
  "clean_up_tokenization_spaces": true,
931
  "eos_token": "</s>",
932
- "extra_ids": 100,
933
  "legacy": false,
934
  "model_max_length": 1000000000000000019884624838656,
935
- "pad_token": "<pad>",
936
  "sp_model_kwargs": {},
937
  "tokenizer_class": "T5Tokenizer",
938
  "unk_token": "<unk>"
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "1": {
12
+ "content": "<s>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "2": {
20
+ "content": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
 
25
  "special": true
26
  }
27
  },
28
+ "additional_special_tokens": [],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  "clean_up_tokenization_spaces": true,
30
  "eos_token": "</s>",
31
+ "extra_ids": 0,
32
  "legacy": false,
33
  "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "<s>",
35
  "sp_model_kwargs": {},
36
  "tokenizer_class": "T5Tokenizer",
37
  "unk_token": "<unk>"