kichan05 commited on
Commit
86f7705
1 Parent(s): 6145547

Upload tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +45 -1
  2. special_tokens_map.json +46 -0
  3. tokenizer.json +445 -12
  4. tokenizer_config.json +400 -1
added_tokens.json CHANGED
@@ -2,5 +2,49 @@
2
  "<|endoftext|>": 50256,
3
  "<||bos||>": 50257,
4
  "<||pad||>": 50258,
5
- "<||unk||>": 50259
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
 
2
  "<|endoftext|>": 50256,
3
  "<||bos||>": 50257,
4
  "<||pad||>": 50258,
5
+ "<||unk||>": 50259,
6
+ "<||unused10||>": 50269,
7
+ "<||unused11||>": 50270,
8
+ "<||unused12||>": 50271,
9
+ "<||unused13||>": 50272,
10
+ "<||unused14||>": 50273,
11
+ "<||unused15||>": 50274,
12
+ "<||unused16||>": 50275,
13
+ "<||unused17||>": 50276,
14
+ "<||unused18||>": 50277,
15
+ "<||unused19||>": 50278,
16
+ "<||unused1||>": 50260,
17
+ "<||unused20||>": 50279,
18
+ "<||unused21||>": 50280,
19
+ "<||unused22||>": 50281,
20
+ "<||unused23||>": 50282,
21
+ "<||unused24||>": 50283,
22
+ "<||unused25||>": 50284,
23
+ "<||unused26||>": 50285,
24
+ "<||unused27||>": 50286,
25
+ "<||unused28||>": 50287,
26
+ "<||unused29||>": 50288,
27
+ "<||unused2||>": 50261,
28
+ "<||unused30||>": 50289,
29
+ "<||unused31||>": 50290,
30
+ "<||unused32||>": 50291,
31
+ "<||unused33||>": 50292,
32
+ "<||unused34||>": 50293,
33
+ "<||unused35||>": 50294,
34
+ "<||unused36||>": 50295,
35
+ "<||unused37||>": 50296,
36
+ "<||unused38||>": 50297,
37
+ "<||unused39||>": 50298,
38
+ "<||unused3||>": 50262,
39
+ "<||unused40||>": 50299,
40
+ "<||unused41||>": 50300,
41
+ "<||unused42||>": 50301,
42
+ "<||unused43||>": 50302,
43
+ "<||unused44||>": 50303,
44
+ "<||unused4||>": 50263,
45
+ "<||unused5||>": 50264,
46
+ "<||unused6||>": 50265,
47
+ "<||unused7||>": 50266,
48
+ "<||unused8||>": 50267,
49
+ "<||unused9||>": 50268
50
  }
special_tokens_map.json CHANGED
@@ -1,4 +1,50 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": "<||bos||>",
3
  "eos_token": {
4
  "content": "<|endoftext|>",
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<||unused1||>",
4
+ "<||unused2||>",
5
+ "<||unused3||>",
6
+ "<||unused4||>",
7
+ "<||unused5||>",
8
+ "<||unused6||>",
9
+ "<||unused7||>",
10
+ "<||unused8||>",
11
+ "<||unused9||>",
12
+ "<||unused10||>",
13
+ "<||unused11||>",
14
+ "<||unused12||>",
15
+ "<||unused13||>",
16
+ "<||unused14||>",
17
+ "<||unused15||>",
18
+ "<||unused16||>",
19
+ "<||unused17||>",
20
+ "<||unused18||>",
21
+ "<||unused19||>",
22
+ "<||unused20||>",
23
+ "<||unused21||>",
24
+ "<||unused22||>",
25
+ "<||unused23||>",
26
+ "<||unused24||>",
27
+ "<||unused25||>",
28
+ "<||unused26||>",
29
+ "<||unused27||>",
30
+ "<||unused28||>",
31
+ "<||unused29||>",
32
+ "<||unused30||>",
33
+ "<||unused31||>",
34
+ "<||unused32||>",
35
+ "<||unused33||>",
36
+ "<||unused34||>",
37
+ "<||unused35||>",
38
+ "<||unused36||>",
39
+ "<||unused37||>",
40
+ "<||unused38||>",
41
+ "<||unused39||>",
42
+ "<||unused40||>",
43
+ "<||unused41||>",
44
+ "<||unused42||>",
45
+ "<||unused43||>",
46
+ "<||unused44||>"
47
+ ],
48
  "bos_token": "<||bos||>",
49
  "eos_token": {
50
  "content": "<|endoftext|>",
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 400,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
@@ -43,6 +38,402 @@
43
  "rstrip": false,
44
  "normalized": false,
45
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
46
  }
47
  ],
48
  "normalizer": null,
@@ -53,10 +444,52 @@
53
  "use_regex": true
54
  },
55
  "post_processor": {
56
- "type": "ByteLevel",
57
- "add_prefix_space": true,
58
- "trim_offsets": true,
59
- "use_regex": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
  },
61
  "decoder": {
62
  "type": "ByteLevel",
@@ -68,8 +501,8 @@
68
  "type": "BPE",
69
  "dropout": null,
70
  "unk_token": null,
71
- "continuing_subword_prefix": null,
72
- "end_of_word_suffix": null,
73
  "fuse_unk": false,
74
  "byte_fallback": false,
75
  "vocab": {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
38
  "rstrip": false,
39
  "normalized": false,
40
  "special": true
41
+ },
42
+ {
43
+ "id": 50260,
44
+ "content": "<||unused1||>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 50261,
53
+ "content": "<||unused2||>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 50262,
62
+ "content": "<||unused3||>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 50263,
71
+ "content": "<||unused4||>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 50264,
80
+ "content": "<||unused5||>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
+ },
87
+ {
88
+ "id": 50265,
89
+ "content": "<||unused6||>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
+ },
96
+ {
97
+ "id": 50266,
98
+ "content": "<||unused7||>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ {
106
+ "id": 50267,
107
+ "content": "<||unused8||>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ {
115
+ "id": 50268,
116
+ "content": "<||unused9||>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
+ },
123
+ {
124
+ "id": 50269,
125
+ "content": "<||unused10||>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
+ },
132
+ {
133
+ "id": 50270,
134
+ "content": "<||unused11||>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
+ },
141
+ {
142
+ "id": 50271,
143
+ "content": "<||unused12||>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
+ },
150
+ {
151
+ "id": 50272,
152
+ "content": "<||unused13||>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
+ },
159
+ {
160
+ "id": 50273,
161
+ "content": "<||unused14||>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ {
169
+ "id": 50274,
170
+ "content": "<||unused15||>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
+ },
177
+ {
178
+ "id": 50275,
179
+ "content": "<||unused16||>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
+ },
186
+ {
187
+ "id": 50276,
188
+ "content": "<||unused17||>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
+ },
195
+ {
196
+ "id": 50277,
197
+ "content": "<||unused18||>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
+ },
204
+ {
205
+ "id": 50278,
206
+ "content": "<||unused19||>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
+ },
213
+ {
214
+ "id": 50279,
215
+ "content": "<||unused20||>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
+ },
222
+ {
223
+ "id": 50280,
224
+ "content": "<||unused21||>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
+ },
231
+ {
232
+ "id": 50281,
233
+ "content": "<||unused22||>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ {
241
+ "id": 50282,
242
+ "content": "<||unused23||>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
+ },
249
+ {
250
+ "id": 50283,
251
+ "content": "<||unused24||>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ {
259
+ "id": 50284,
260
+ "content": "<||unused25||>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
+ },
267
+ {
268
+ "id": 50285,
269
+ "content": "<||unused26||>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
+ },
276
+ {
277
+ "id": 50286,
278
+ "content": "<||unused27||>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
+ },
285
+ {
286
+ "id": 50287,
287
+ "content": "<||unused28||>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
+ },
294
+ {
295
+ "id": 50288,
296
+ "content": "<||unused29||>",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
+ },
303
+ {
304
+ "id": 50289,
305
+ "content": "<||unused30||>",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
+ },
312
+ {
313
+ "id": 50290,
314
+ "content": "<||unused31||>",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
+ },
321
+ {
322
+ "id": 50291,
323
+ "content": "<||unused32||>",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
+ },
330
+ {
331
+ "id": 50292,
332
+ "content": "<||unused33||>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
+ },
339
+ {
340
+ "id": 50293,
341
+ "content": "<||unused34||>",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
+ },
348
+ {
349
+ "id": 50294,
350
+ "content": "<||unused35||>",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
+ },
357
+ {
358
+ "id": 50295,
359
+ "content": "<||unused36||>",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
+ },
366
+ {
367
+ "id": 50296,
368
+ "content": "<||unused37||>",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
+ },
375
+ {
376
+ "id": 50297,
377
+ "content": "<||unused38||>",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
+ },
384
+ {
385
+ "id": 50298,
386
+ "content": "<||unused39||>",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
+ },
393
+ {
394
+ "id": 50299,
395
+ "content": "<||unused40||>",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
+ },
402
+ {
403
+ "id": 50300,
404
+ "content": "<||unused41||>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
+ },
411
+ {
412
+ "id": 50301,
413
+ "content": "<||unused42||>",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
+ },
420
+ {
421
+ "id": 50302,
422
+ "content": "<||unused43||>",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
+ },
429
+ {
430
+ "id": 50303,
431
+ "content": "<||unused44||>",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
  }
438
  ],
439
  "normalizer": null,
 
444
  "use_regex": true
445
  },
446
  "post_processor": {
447
+ "type": "TemplateProcessing",
448
+ "single": [
449
+ {
450
+ "SpecialToken": {
451
+ "id": "<||bos||>",
452
+ "type_id": 0
453
+ }
454
+ },
455
+ {
456
+ "Sequence": {
457
+ "id": "A",
458
+ "type_id": 0
459
+ }
460
+ }
461
+ ],
462
+ "pair": [
463
+ {
464
+ "SpecialToken": {
465
+ "id": "<||bos||>",
466
+ "type_id": 0
467
+ }
468
+ },
469
+ {
470
+ "Sequence": {
471
+ "id": "A",
472
+ "type_id": 0
473
+ }
474
+ },
475
+ {
476
+ "Sequence": {
477
+ "id": "B",
478
+ "type_id": 1
479
+ }
480
+ }
481
+ ],
482
+ "special_tokens": {
483
+ "<||bos||>": {
484
+ "id": "<||bos||>",
485
+ "ids": [
486
+ 50257
487
+ ],
488
+ "tokens": [
489
+ "<||bos||>"
490
+ ]
491
+ }
492
+ }
493
  },
494
  "decoder": {
495
  "type": "ByteLevel",
 
501
  "type": "BPE",
502
  "dropout": null,
503
  "unk_token": null,
504
+ "continuing_subword_prefix": "",
505
+ "end_of_word_suffix": "",
506
  "fuse_unk": false,
507
  "byte_fallback": false,
508
  "vocab": {
tokenizer_config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "add_bos_token": false,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
  "50256": {
@@ -33,14 +33,413 @@
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  }
37
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38
  "bos_token": "<||bos||>",
39
  "clean_up_tokenization_spaces": true,
40
  "eos_token": "<|endoftext|>",
41
  "errors": "replace",
42
  "model_max_length": 8192,
43
  "pad_token": "<||pad||>",
 
44
  "tokenizer_class": "GPT2Tokenizer",
45
  "unk_token": "<||unk||>"
46
  }
 
1
  {
2
+ "add_bos_token": true,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
  "50256": {
 
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
+ },
37
+ "50260": {
38
+ "content": "<||unused1||>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "50261": {
46
+ "content": "<||unused2||>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "50262": {
54
+ "content": "<||unused3||>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "50263": {
62
+ "content": "<||unused4||>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "50264": {
70
+ "content": "<||unused5||>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "50265": {
78
+ "content": "<||unused6||>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "50266": {
86
+ "content": "<||unused7||>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "50267": {
94
+ "content": "<||unused8||>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "50268": {
102
+ "content": "<||unused9||>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "50269": {
110
+ "content": "<||unused10||>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "50270": {
118
+ "content": "<||unused11||>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "50271": {
126
+ "content": "<||unused12||>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "50272": {
134
+ "content": "<||unused13||>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "50273": {
142
+ "content": "<||unused14||>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "50274": {
150
+ "content": "<||unused15||>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "50275": {
158
+ "content": "<||unused16||>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "50276": {
166
+ "content": "<||unused17||>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "50277": {
174
+ "content": "<||unused18||>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "50278": {
182
+ "content": "<||unused19||>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "50279": {
190
+ "content": "<||unused20||>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "50280": {
198
+ "content": "<||unused21||>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "50281": {
206
+ "content": "<||unused22||>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "50282": {
214
+ "content": "<||unused23||>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "50283": {
222
+ "content": "<||unused24||>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "50284": {
230
+ "content": "<||unused25||>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "50285": {
238
+ "content": "<||unused26||>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "50286": {
246
+ "content": "<||unused27||>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "50287": {
254
+ "content": "<||unused28||>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "50288": {
262
+ "content": "<||unused29||>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "50289": {
270
+ "content": "<||unused30||>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "50290": {
278
+ "content": "<||unused31||>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "50291": {
286
+ "content": "<||unused32||>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "50292": {
294
+ "content": "<||unused33||>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "50293": {
302
+ "content": "<||unused34||>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "50294": {
310
+ "content": "<||unused35||>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "50295": {
318
+ "content": "<||unused36||>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "50296": {
326
+ "content": "<||unused37||>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "50297": {
334
+ "content": "<||unused38||>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "50298": {
342
+ "content": "<||unused39||>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "50299": {
350
+ "content": "<||unused40||>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "50300": {
358
+ "content": "<||unused41||>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "50301": {
366
+ "content": "<||unused42||>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "50302": {
374
+ "content": "<||unused43||>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "50303": {
382
+ "content": "<||unused44||>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
  }
389
  },
390
+ "additional_special_tokens": [
391
+ "<||unused1||>",
392
+ "<||unused2||>",
393
+ "<||unused3||>",
394
+ "<||unused4||>",
395
+ "<||unused5||>",
396
+ "<||unused6||>",
397
+ "<||unused7||>",
398
+ "<||unused8||>",
399
+ "<||unused9||>",
400
+ "<||unused10||>",
401
+ "<||unused11||>",
402
+ "<||unused12||>",
403
+ "<||unused13||>",
404
+ "<||unused14||>",
405
+ "<||unused15||>",
406
+ "<||unused16||>",
407
+ "<||unused17||>",
408
+ "<||unused18||>",
409
+ "<||unused19||>",
410
+ "<||unused20||>",
411
+ "<||unused21||>",
412
+ "<||unused22||>",
413
+ "<||unused23||>",
414
+ "<||unused24||>",
415
+ "<||unused25||>",
416
+ "<||unused26||>",
417
+ "<||unused27||>",
418
+ "<||unused28||>",
419
+ "<||unused29||>",
420
+ "<||unused30||>",
421
+ "<||unused31||>",
422
+ "<||unused32||>",
423
+ "<||unused33||>",
424
+ "<||unused34||>",
425
+ "<||unused35||>",
426
+ "<||unused36||>",
427
+ "<||unused37||>",
428
+ "<||unused38||>",
429
+ "<||unused39||>",
430
+ "<||unused40||>",
431
+ "<||unused41||>",
432
+ "<||unused42||>",
433
+ "<||unused43||>",
434
+ "<||unused44||>"
435
+ ],
436
  "bos_token": "<||bos||>",
437
  "clean_up_tokenization_spaces": true,
438
  "eos_token": "<|endoftext|>",
439
  "errors": "replace",
440
  "model_max_length": 8192,
441
  "pad_token": "<||pad||>",
442
+ "padding_side": "right",
443
  "tokenizer_class": "GPT2Tokenizer",
444
  "unk_token": "<||unk||>"
445
  }