zhuqi commited on
Commit
afece57
1 Parent(s): 525085d

Upload with huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +4 -2
  2. pytorch_model.bin +1 -1
  3. special_tokens_map.json +107 -1
  4. tokenizer.json +206 -206
  5. tokenizer_config.json +112 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
@@ -7,11 +7,13 @@
7
  "d_kv": 64,
8
  "d_model": 512,
9
  "decoder_start_token_id": 0,
 
10
  "dropout_rate": 0.1,
11
  "eos_token_id": 1,
12
  "feed_forward_proj": "relu",
13
  "initializer_factor": 1.0,
14
  "is_encoder_decoder": true,
 
15
  "layer_norm_epsilon": 1e-06,
16
  "model_type": "t5",
17
  "n_positions": 512,
@@ -52,7 +54,7 @@
52
  }
53
  },
54
  "torch_dtype": "float32",
55
- "transformers_version": "4.18.0",
56
  "use_cache": false,
57
  "vocab_size": 32100
58
  }
1
  {
2
+ "_name_or_path": "/zhangpai23/zhuqi/pre-trained-models/t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
7
  "d_kv": 64,
8
  "d_model": 512,
9
  "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
  "dropout_rate": 0.1,
12
  "eos_token_id": 1,
13
  "feed_forward_proj": "relu",
14
  "initializer_factor": 1.0,
15
  "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
19
  "n_positions": 512,
54
  }
55
  },
56
  "torch_dtype": "float32",
57
+ "transformers_version": "4.20.1",
58
  "use_cache": false,
59
  "vocab_size": 32100
60
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4953531d3e35ba8566e6740274a987e85f79c83b54ec7cb028a9fe3ba85016c5
3
  size 242012923
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e296719e4423d7981a319b323d94c857b22b7a70552664a2b44a55eed96a52b
3
  size 242012923
special_tokens_map.json CHANGED
@@ -1 +1,107 @@
1
- {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
tokenizer.json CHANGED
@@ -5,930 +5,930 @@
5
  "added_tokens": [
6
  {
7
  "id": 0,
8
- "special": true,
9
  "content": "<pad>",
10
  "single_word": false,
11
  "lstrip": false,
12
  "rstrip": false,
13
- "normalized": false
 
14
  },
15
  {
16
  "id": 1,
17
- "special": true,
18
  "content": "</s>",
19
  "single_word": false,
20
  "lstrip": false,
21
  "rstrip": false,
22
- "normalized": false
 
23
  },
24
  {
25
  "id": 2,
26
- "special": true,
27
  "content": "<unk>",
28
  "single_word": false,
29
  "lstrip": false,
30
  "rstrip": false,
31
- "normalized": false
 
32
  },
33
  {
34
  "id": 32000,
35
- "special": true,
36
  "content": "<extra_id_99>",
37
  "single_word": false,
38
  "lstrip": false,
39
  "rstrip": false,
40
- "normalized": false
 
41
  },
42
  {
43
  "id": 32001,
44
- "special": true,
45
  "content": "<extra_id_98>",
46
  "single_word": false,
47
  "lstrip": false,
48
  "rstrip": false,
49
- "normalized": false
 
50
  },
51
  {
52
  "id": 32002,
53
- "special": true,
54
  "content": "<extra_id_97>",
55
  "single_word": false,
56
  "lstrip": false,
57
  "rstrip": false,
58
- "normalized": false
 
59
  },
60
  {
61
  "id": 32003,
62
- "special": true,
63
  "content": "<extra_id_96>",
64
  "single_word": false,
65
  "lstrip": false,
66
  "rstrip": false,
67
- "normalized": false
 
68
  },
69
  {
70
  "id": 32004,
71
- "special": true,
72
  "content": "<extra_id_95>",
73
  "single_word": false,
74
  "lstrip": false,
75
  "rstrip": false,
76
- "normalized": false
 
77
  },
78
  {
79
  "id": 32005,
80
- "special": true,
81
  "content": "<extra_id_94>",
82
  "single_word": false,
83
  "lstrip": false,
84
  "rstrip": false,
85
- "normalized": false
 
86
  },
87
  {
88
  "id": 32006,
89
- "special": true,
90
  "content": "<extra_id_93>",
91
  "single_word": false,
92
  "lstrip": false,
93
  "rstrip": false,
94
- "normalized": false
 
95
  },
96
  {
97
  "id": 32007,
98
- "special": true,
99
  "content": "<extra_id_92>",
100
  "single_word": false,
101
  "lstrip": false,
102
  "rstrip": false,
103
- "normalized": false
 
104
  },
105
  {
106
  "id": 32008,
107
- "special": true,
108
  "content": "<extra_id_91>",
109
  "single_word": false,
110
  "lstrip": false,
111
  "rstrip": false,
112
- "normalized": false
 
113
  },
114
  {
115
  "id": 32009,
116
- "special": true,
117
  "content": "<extra_id_90>",
118
  "single_word": false,
119
  "lstrip": false,
120
  "rstrip": false,
121
- "normalized": false
 
122
  },
123
  {
124
  "id": 32010,
125
- "special": true,
126
  "content": "<extra_id_89>",
127
  "single_word": false,
128
  "lstrip": false,
129
  "rstrip": false,
130
- "normalized": false
 
131
  },
132
  {
133
  "id": 32011,
134
- "special": true,
135
  "content": "<extra_id_88>",
136
  "single_word": false,
137
  "lstrip": false,
138
  "rstrip": false,
139
- "normalized": false
 
140
  },
141
  {
142
  "id": 32012,
143
- "special": true,
144
  "content": "<extra_id_87>",
145
  "single_word": false,
146
  "lstrip": false,
147
  "rstrip": false,
148
- "normalized": false
 
149
  },
150
  {
151
  "id": 32013,
152
- "special": true,
153
  "content": "<extra_id_86>",
154
  "single_word": false,
155
  "lstrip": false,
156
  "rstrip": false,
157
- "normalized": false
 
158
  },
159
  {
160
  "id": 32014,
161
- "special": true,
162
  "content": "<extra_id_85>",
163
  "single_word": false,
164
  "lstrip": false,
165
  "rstrip": false,
166
- "normalized": false
 
167
  },
168
  {
169
  "id": 32015,
170
- "special": true,
171
  "content": "<extra_id_84>",
172
  "single_word": false,
173
  "lstrip": false,
174
  "rstrip": false,
175
- "normalized": false
 
176
  },
177
  {
178
  "id": 32016,
179
- "special": true,
180
  "content": "<extra_id_83>",
181
  "single_word": false,
182
  "lstrip": false,
183
  "rstrip": false,
184
- "normalized": false
 
185
  },
186
  {
187
  "id": 32017,
188
- "special": true,
189
  "content": "<extra_id_82>",
190
  "single_word": false,
191
  "lstrip": false,
192
  "rstrip": false,
193
- "normalized": false
 
194
  },
195
  {
196
  "id": 32018,
197
- "special": true,
198
  "content": "<extra_id_81>",
199
  "single_word": false,
200
  "lstrip": false,
201
  "rstrip": false,
202
- "normalized": false
 
203
  },
204
  {
205
  "id": 32019,
206
- "special": true,
207
  "content": "<extra_id_80>",
208
  "single_word": false,
209
  "lstrip": false,
210
  "rstrip": false,
211
- "normalized": false
 
212
  },
213
  {
214
  "id": 32020,
215
- "special": true,
216
  "content": "<extra_id_79>",
217
  "single_word": false,
218
  "lstrip": false,
219
  "rstrip": false,
220
- "normalized": false
 
221
  },
222
  {
223
  "id": 32021,
224
- "special": true,
225
  "content": "<extra_id_78>",
226
  "single_word": false,
227
  "lstrip": false,
228
  "rstrip": false,
229
- "normalized": false
 
230
  },
231
  {
232
  "id": 32022,
233
- "special": true,
234
  "content": "<extra_id_77>",
235
  "single_word": false,
236
  "lstrip": false,
237
  "rstrip": false,
238
- "normalized": false
 
239
  },
240
  {
241
  "id": 32023,
242
- "special": true,
243
  "content": "<extra_id_76>",
244
  "single_word": false,
245
  "lstrip": false,
246
  "rstrip": false,
247
- "normalized": false
 
248
  },
249
  {
250
  "id": 32024,
251
- "special": true,
252
  "content": "<extra_id_75>",
253
  "single_word": false,
254
  "lstrip": false,
255
  "rstrip": false,
256
- "normalized": false
 
257
  },
258
  {
259
  "id": 32025,
260
- "special": true,
261
  "content": "<extra_id_74>",
262
  "single_word": false,
263
  "lstrip": false,
264
  "rstrip": false,
265
- "normalized": false
 
266
  },
267
  {
268
  "id": 32026,
269
- "special": true,
270
  "content": "<extra_id_73>",
271
  "single_word": false,
272
  "lstrip": false,
273
  "rstrip": false,
274
- "normalized": false
 
275
  },
276
  {
277
  "id": 32027,
278
- "special": true,
279
  "content": "<extra_id_72>",
280
  "single_word": false,
281
  "lstrip": false,
282
  "rstrip": false,
283
- "normalized": false
 
284
  },
285
  {
286
  "id": 32028,
287
- "special": true,
288
  "content": "<extra_id_71>",
289
  "single_word": false,
290
  "lstrip": false,
291
  "rstrip": false,
292
- "normalized": false
 
293
  },
294
  {
295
  "id": 32029,
296
- "special": true,
297
  "content": "<extra_id_70>",
298
  "single_word": false,
299
  "lstrip": false,
300
  "rstrip": false,
301
- "normalized": false
 
302
  },
303
  {
304
  "id": 32030,
305
- "special": true,
306
  "content": "<extra_id_69>",
307
  "single_word": false,
308
  "lstrip": false,
309
  "rstrip": false,
310
- "normalized": false
 
311
  },
312
  {
313
  "id": 32031,
314
- "special": true,
315
  "content": "<extra_id_68>",
316
  "single_word": false,
317
  "lstrip": false,
318
  "rstrip": false,
319
- "normalized": false
 
320
  },
321
  {
322
  "id": 32032,
323
- "special": true,
324
  "content": "<extra_id_67>",
325
  "single_word": false,
326
  "lstrip": false,
327
  "rstrip": false,
328
- "normalized": false
 
329
  },
330
  {
331
  "id": 32033,
332
- "special": true,
333
  "content": "<extra_id_66>",
334
  "single_word": false,
335
  "lstrip": false,
336
  "rstrip": false,
337
- "normalized": false
 
338
  },
339
  {
340
  "id": 32034,
341
- "special": true,
342
  "content": "<extra_id_65>",
343
  "single_word": false,
344
  "lstrip": false,
345
  "rstrip": false,
346
- "normalized": false
 
347
  },
348
  {
349
  "id": 32035,
350
- "special": true,
351
  "content": "<extra_id_64>",
352
  "single_word": false,
353
  "lstrip": false,
354
  "rstrip": false,
355
- "normalized": false
 
356
  },
357
  {
358
  "id": 32036,
359
- "special": true,
360
  "content": "<extra_id_63>",
361
  "single_word": false,
362
  "lstrip": false,
363
  "rstrip": false,
364
- "normalized": false
 
365
  },
366
  {
367
  "id": 32037,
368
- "special": true,
369
  "content": "<extra_id_62>",
370
  "single_word": false,
371
  "lstrip": false,
372
  "rstrip": false,
373
- "normalized": false
 
374
  },
375
  {
376
  "id": 32038,
377
- "special": true,
378
  "content": "<extra_id_61>",
379
  "single_word": false,
380
  "lstrip": false,
381
  "rstrip": false,
382
- "normalized": false
 
383
  },
384
  {
385
  "id": 32039,
386
- "special": true,
387
  "content": "<extra_id_60>",
388
  "single_word": false,
389
  "lstrip": false,
390
  "rstrip": false,
391
- "normalized": false
 
392
  },
393
  {
394
  "id": 32040,
395
- "special": true,
396
  "content": "<extra_id_59>",
397
  "single_word": false,
398
  "lstrip": false,
399
  "rstrip": false,
400
- "normalized": false
 
401
  },
402
  {
403
  "id": 32041,
404
- "special": true,
405
  "content": "<extra_id_58>",
406
  "single_word": false,
407
  "lstrip": false,
408
  "rstrip": false,
409
- "normalized": false
 
410
  },
411
  {
412
  "id": 32042,
413
- "special": true,
414
  "content": "<extra_id_57>",
415
  "single_word": false,
416
  "lstrip": false,
417
  "rstrip": false,
418
- "normalized": false
 
419
  },
420
  {
421
  "id": 32043,
422
- "special": true,
423
  "content": "<extra_id_56>",
424
  "single_word": false,
425
  "lstrip": false,
426
  "rstrip": false,
427
- "normalized": false
 
428
  },
429
  {
430
  "id": 32044,
431
- "special": true,
432
  "content": "<extra_id_55>",
433
  "single_word": false,
434
  "lstrip": false,
435
  "rstrip": false,
436
- "normalized": false
 
437
  },
438
  {
439
  "id": 32045,
440
- "special": true,
441
  "content": "<extra_id_54>",
442
  "single_word": false,
443
  "lstrip": false,
444
  "rstrip": false,
445
- "normalized": false
 
446
  },
447
  {
448
  "id": 32046,
449
- "special": true,
450
  "content": "<extra_id_53>",
451
  "single_word": false,
452
  "lstrip": false,
453
  "rstrip": false,
454
- "normalized": false
 
455
  },
456
  {
457
  "id": 32047,
458
- "special": true,
459
  "content": "<extra_id_52>",
460
  "single_word": false,
461
  "lstrip": false,
462
  "rstrip": false,
463
- "normalized": false
 
464
  },
465
  {
466
  "id": 32048,
467
- "special": true,
468
  "content": "<extra_id_51>",
469
  "single_word": false,
470
  "lstrip": false,
471
  "rstrip": false,
472
- "normalized": false
 
473
  },
474
  {
475
  "id": 32049,
476
- "special": true,
477
  "content": "<extra_id_50>",
478
  "single_word": false,
479
  "lstrip": false,
480
  "rstrip": false,
481
- "normalized": false
 
482
  },
483
  {
484
  "id": 32050,
485
- "special": true,
486
  "content": "<extra_id_49>",
487
  "single_word": false,
488
  "lstrip": false,
489
  "rstrip": false,
490
- "normalized": false
 
491
  },
492
  {
493
  "id": 32051,
494
- "special": true,
495
  "content": "<extra_id_48>",
496
  "single_word": false,
497
  "lstrip": false,
498
  "rstrip": false,
499
- "normalized": false
 
500
  },
501
  {
502
  "id": 32052,
503
- "special": true,
504
  "content": "<extra_id_47>",
505
  "single_word": false,
506
  "lstrip": false,
507
  "rstrip": false,
508
- "normalized": false
 
509
  },
510
  {
511
  "id": 32053,
512
- "special": true,
513
  "content": "<extra_id_46>",
514
  "single_word": false,
515
  "lstrip": false,
516
  "rstrip": false,
517
- "normalized": false
 
518
  },
519
  {
520
  "id": 32054,
521
- "special": true,
522
  "content": "<extra_id_45>",
523
  "single_word": false,
524
  "lstrip": false,
525
  "rstrip": false,
526
- "normalized": false
 
527
  },
528
  {
529
  "id": 32055,
530
- "special": true,
531
  "content": "<extra_id_44>",
532
  "single_word": false,
533
  "lstrip": false,
534
  "rstrip": false,
535
- "normalized": false
 
536
  },
537
  {
538
  "id": 32056,
539
- "special": true,
540
  "content": "<extra_id_43>",
541
  "single_word": false,
542
  "lstrip": false,
543
  "rstrip": false,
544
- "normalized": false
 
545
  },
546
  {
547
  "id": 32057,
548
- "special": true,
549
  "content": "<extra_id_42>",
550
  "single_word": false,
551
  "lstrip": false,
552
  "rstrip": false,
553
- "normalized": false
 
554
  },
555
  {
556
  "id": 32058,
557
- "special": true,
558
  "content": "<extra_id_41>",
559
  "single_word": false,
560
  "lstrip": false,
561
  "rstrip": false,
562
- "normalized": false
 
563
  },
564
  {
565
  "id": 32059,
566
- "special": true,
567
  "content": "<extra_id_40>",
568
  "single_word": false,
569
  "lstrip": false,
570
  "rstrip": false,
571
- "normalized": false
 
572
  },
573
  {
574
  "id": 32060,
575
- "special": true,
576
  "content": "<extra_id_39>",
577
  "single_word": false,
578
  "lstrip": false,
579
  "rstrip": false,
580
- "normalized": false
 
581
  },
582
  {
583
  "id": 32061,
584
- "special": true,
585
  "content": "<extra_id_38>",
586
  "single_word": false,
587
  "lstrip": false,
588
  "rstrip": false,
589
- "normalized": false
 
590
  },
591
  {
592
  "id": 32062,
593
- "special": true,
594
  "content": "<extra_id_37>",
595
  "single_word": false,
596
  "lstrip": false,
597
  "rstrip": false,
598
- "normalized": false
 
599
  },
600
  {
601
  "id": 32063,
602
- "special": true,
603
  "content": "<extra_id_36>",
604
  "single_word": false,
605
  "lstrip": false,
606
  "rstrip": false,
607
- "normalized": false
 
608
  },
609
  {
610
  "id": 32064,
611
- "special": true,
612
  "content": "<extra_id_35>",
613
  "single_word": false,
614
  "lstrip": false,
615
  "rstrip": false,
616
- "normalized": false
 
617
  },
618
  {
619
  "id": 32065,
620
- "special": true,
621
  "content": "<extra_id_34>",
622
  "single_word": false,
623
  "lstrip": false,
624
  "rstrip": false,
625
- "normalized": false
 
626
  },
627
  {
628
  "id": 32066,
629
- "special": true,
630
  "content": "<extra_id_33>",
631
  "single_word": false,
632
  "lstrip": false,
633
  "rstrip": false,
634
- "normalized": false
 
635
  },
636
  {
637
  "id": 32067,
638
- "special": true,
639
  "content": "<extra_id_32>",
640
  "single_word": false,
641
  "lstrip": false,
642
  "rstrip": false,
643
- "normalized": false
 
644
  },
645
  {
646
  "id": 32068,
647
- "special": true,
648
  "content": "<extra_id_31>",
649
  "single_word": false,
650
  "lstrip": false,
651
  "rstrip": false,
652
- "normalized": false
 
653
  },
654
  {
655
  "id": 32069,
656
- "special": true,
657
  "content": "<extra_id_30>",
658
  "single_word": false,
659
  "lstrip": false,
660
  "rstrip": false,
661
- "normalized": false
 
662
  },
663
  {
664
  "id": 32070,
665
- "special": true,
666
  "content": "<extra_id_29>",
667
  "single_word": false,
668
  "lstrip": false,
669
  "rstrip": false,
670
- "normalized": false
 
671
  },
672
  {
673
  "id": 32071,
674
- "special": true,
675
  "content": "<extra_id_28>",
676
  "single_word": false,
677
  "lstrip": false,
678
  "rstrip": false,
679
- "normalized": false
 
680
  },
681
  {
682
  "id": 32072,
683
- "special": true,
684
  "content": "<extra_id_27>",
685
  "single_word": false,
686
  "lstrip": false,
687
  "rstrip": false,
688
- "normalized": false
 
689
  },
690
  {
691
  "id": 32073,
692
- "special": true,
693
  "content": "<extra_id_26>",
694
  "single_word": false,
695
  "lstrip": false,
696
  "rstrip": false,
697
- "normalized": false
 
698
  },
699
  {
700
  "id": 32074,
701
- "special": true,
702
  "content": "<extra_id_25>",
703
  "single_word": false,
704
  "lstrip": false,
705
  "rstrip": false,
706
- "normalized": false
 
707
  },
708
  {
709
  "id": 32075,
710
- "special": true,
711
  "content": "<extra_id_24>",
712
  "single_word": false,
713
  "lstrip": false,
714
  "rstrip": false,
715
- "normalized": false
 
716
  },
717
  {
718
  "id": 32076,
719
- "special": true,
720
  "content": "<extra_id_23>",
721
  "single_word": false,
722
  "lstrip": false,
723
  "rstrip": false,
724
- "normalized": false
 
725
  },
726
  {
727
  "id": 32077,
728
- "special": true,
729
  "content": "<extra_id_22>",
730
  "single_word": false,
731
  "lstrip": false,
732
  "rstrip": false,
733
- "normalized": false
 
734
  },
735
  {
736
  "id": 32078,
737
- "special": true,
738
  "content": "<extra_id_21>",
739
  "single_word": false,
740
  "lstrip": false,
741
  "rstrip": false,
742
- "normalized": false
 
743
  },
744
  {
745
  "id": 32079,
746
- "special": true,
747
  "content": "<extra_id_20>",
748
  "single_word": false,
749
  "lstrip": false,
750
  "rstrip": false,
751
- "normalized": false
 
752
  },
753
  {
754
  "id": 32080,
755
- "special": true,
756
  "content": "<extra_id_19>",
757
  "single_word": false,
758
  "lstrip": false,
759
  "rstrip": false,
760
- "normalized": false
 
761
  },
762
  {
763
  "id": 32081,
764
- "special": true,
765
  "content": "<extra_id_18>",
766
  "single_word": false,
767
  "lstrip": false,
768
  "rstrip": false,
769
- "normalized": false
 
770
  },
771
  {
772
  "id": 32082,
773
- "special": true,
774
  "content": "<extra_id_17>",
775
  "single_word": false,
776
  "lstrip": false,
777
  "rstrip": false,
778
- "normalized": false
 
779
  },
780
  {
781
  "id": 32083,
782
- "special": true,
783
  "content": "<extra_id_16>",
784
  "single_word": false,
785
  "lstrip": false,
786
  "rstrip": false,
787
- "normalized": false
 
788
  },
789
  {
790
  "id": 32084,
791
- "special": true,
792
  "content": "<extra_id_15>",
793
  "single_word": false,
794
  "lstrip": false,
795
  "rstrip": false,
796
- "normalized": false
 
797
  },
798
  {
799
  "id": 32085,
800
- "special": true,
801
  "content": "<extra_id_14>",
802
  "single_word": false,
803
  "lstrip": false,
804
  "rstrip": false,
805
- "normalized": false
 
806
  },
807
  {
808
  "id": 32086,
809
- "special": true,
810
  "content": "<extra_id_13>",
811
  "single_word": false,
812
  "lstrip": false,
813
  "rstrip": false,
814
- "normalized": false
 
815
  },
816
  {
817
  "id": 32087,
818
- "special": true,
819
  "content": "<extra_id_12>",
820
  "single_word": false,
821
  "lstrip": false,
822
  "rstrip": false,
823
- "normalized": false
 
824
  },
825
  {
826
  "id": 32088,
827
- "special": true,
828
  "content": "<extra_id_11>",
829
  "single_word": false,
830
  "lstrip": false,
831
  "rstrip": false,
832
- "normalized": false
 
833
  },
834
  {
835
  "id": 32089,
836
- "special": true,
837
  "content": "<extra_id_10>",
838
  "single_word": false,
839
  "lstrip": false,
840
  "rstrip": false,
841
- "normalized": false
 
842
  },
843
  {
844
  "id": 32090,
845
- "special": true,
846
  "content": "<extra_id_9>",
847
  "single_word": false,
848
  "lstrip": false,
849
  "rstrip": false,
850
- "normalized": false
 
851
  },
852
  {
853
  "id": 32091,
854
- "special": true,
855
  "content": "<extra_id_8>",
856
  "single_word": false,
857
  "lstrip": false,
858
  "rstrip": false,
859
- "normalized": false
 
860
  },
861
  {
862
  "id": 32092,
863
- "special": true,
864
  "content": "<extra_id_7>",
865
  "single_word": false,
866
  "lstrip": false,
867
  "rstrip": false,
868
- "normalized": false
 
869
  },
870
  {
871
  "id": 32093,
872
- "special": true,
873
  "content": "<extra_id_6>",
874
  "single_word": false,
875
  "lstrip": false,
876
  "rstrip": false,
877
- "normalized": false
 
878
  },
879
  {
880
  "id": 32094,
881
- "special": true,
882
  "content": "<extra_id_5>",
883
  "single_word": false,
884
  "lstrip": false,
885
  "rstrip": false,
886
- "normalized": false
 
887
  },
888
  {
889
  "id": 32095,
890
- "special": true,
891
  "content": "<extra_id_4>",
892
  "single_word": false,
893
  "lstrip": false,
894
  "rstrip": false,
895
- "normalized": false
 
896
  },
897
  {
898
  "id": 32096,
899
- "special": true,
900
  "content": "<extra_id_3>",
901
  "single_word": false,
902
  "lstrip": false,
903
  "rstrip": false,
904
- "normalized": false
 
905
  },
906
  {
907
  "id": 32097,
908
- "special": true,
909
  "content": "<extra_id_2>",
910
  "single_word": false,
911
  "lstrip": false,
912
  "rstrip": false,
913
- "normalized": false
 
914
  },
915
  {
916
  "id": 32098,
917
- "special": true,
918
  "content": "<extra_id_1>",
919
  "single_word": false,
920
  "lstrip": false,
921
  "rstrip": false,
922
- "normalized": false
 
923
  },
924
  {
925
  "id": 32099,
926
- "special": true,
927
  "content": "<extra_id_0>",
928
  "single_word": false,
929
  "lstrip": false,
930
  "rstrip": false,
931
- "normalized": false
 
932
  }
933
  ],
934
  "normalizer": {
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
8
  "content": "<pad>",
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
  },
15
  {
16
  "id": 1,
 
17
  "content": "</s>",
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
  },
24
  {
25
  "id": 2,
 
26
  "content": "<unk>",
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
  },
33
  {
34
  "id": 32000,
 
35
  "content": "<extra_id_99>",
36
  "single_word": false,
37
  "lstrip": false,
38
  "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
  },
42
  {
43
  "id": 32001,
 
44
  "content": "<extra_id_98>",
45
  "single_word": false,
46
  "lstrip": false,
47
  "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
  },
51
  {
52
  "id": 32002,
 
53
  "content": "<extra_id_97>",
54
  "single_word": false,
55
  "lstrip": false,
56
  "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
  },
60
  {
61
  "id": 32003,
 
62
  "content": "<extra_id_96>",
63
  "single_word": false,
64
  "lstrip": false,
65
  "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
  },
69
  {
70
  "id": 32004,
 
71
  "content": "<extra_id_95>",
72
  "single_word": false,
73
  "lstrip": false,
74
  "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
  },
78
  {
79
  "id": 32005,
 
80
  "content": "<extra_id_94>",
81
  "single_word": false,
82
  "lstrip": false,
83
  "rstrip": false,
84
+ "normalized": false,
85
+ "special": true
86
  },
87
  {
88
  "id": 32006,
 
89
  "content": "<extra_id_93>",
90
  "single_word": false,
91
  "lstrip": false,
92
  "rstrip": false,
93
+ "normalized": false,
94
+ "special": true
95
  },
96
  {
97
  "id": 32007,
 
98
  "content": "<extra_id_92>",
99
  "single_word": false,
100
  "lstrip": false,
101
  "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
  },
105
  {
106
  "id": 32008,
 
107
  "content": "<extra_id_91>",
108
  "single_word": false,
109
  "lstrip": false,
110
  "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
  },
114
  {
115
  "id": 32009,
 
116
  "content": "<extra_id_90>",
117
  "single_word": false,
118
  "lstrip": false,
119
  "rstrip": false,
120
+ "normalized": false,
121
+ "special": true
122
  },
123
  {
124
  "id": 32010,
 
125
  "content": "<extra_id_89>",
126
  "single_word": false,
127
  "lstrip": false,
128
  "rstrip": false,
129
+ "normalized": false,
130
+ "special": true
131
  },
132
  {
133
  "id": 32011,
 
134
  "content": "<extra_id_88>",
135
  "single_word": false,
136
  "lstrip": false,
137
  "rstrip": false,
138
+ "normalized": false,
139
+ "special": true
140
  },
141
  {
142
  "id": 32012,
 
143
  "content": "<extra_id_87>",
144
  "single_word": false,
145
  "lstrip": false,
146
  "rstrip": false,
147
+ "normalized": false,
148
+ "special": true
149
  },
150
  {
151
  "id": 32013,
 
152
  "content": "<extra_id_86>",
153
  "single_word": false,
154
  "lstrip": false,
155
  "rstrip": false,
156
+ "normalized": false,
157
+ "special": true
158
  },
159
  {
160
  "id": 32014,
 
161
  "content": "<extra_id_85>",
162
  "single_word": false,
163
  "lstrip": false,
164
  "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
  },
168
  {
169
  "id": 32015,
 
170
  "content": "<extra_id_84>",
171
  "single_word": false,
172
  "lstrip": false,
173
  "rstrip": false,
174
+ "normalized": false,
175
+ "special": true
176
  },
177
  {
178
  "id": 32016,
 
179
  "content": "<extra_id_83>",
180
  "single_word": false,
181
  "lstrip": false,
182
  "rstrip": false,
183
+ "normalized": false,
184
+ "special": true
185
  },
186
  {
187
  "id": 32017,
 
188
  "content": "<extra_id_82>",
189
  "single_word": false,
190
  "lstrip": false,
191
  "rstrip": false,
192
+ "normalized": false,
193
+ "special": true
194
  },
195
  {
196
  "id": 32018,
 
197
  "content": "<extra_id_81>",
198
  "single_word": false,
199
  "lstrip": false,
200
  "rstrip": false,
201
+ "normalized": false,
202
+ "special": true
203
  },
204
  {
205
  "id": 32019,
 
206
  "content": "<extra_id_80>",
207
  "single_word": false,
208
  "lstrip": false,
209
  "rstrip": false,
210
+ "normalized": false,
211
+ "special": true
212
  },
213
  {
214
  "id": 32020,
 
215
  "content": "<extra_id_79>",
216
  "single_word": false,
217
  "lstrip": false,
218
  "rstrip": false,
219
+ "normalized": false,
220
+ "special": true
221
  },
222
  {
223
  "id": 32021,
 
224
  "content": "<extra_id_78>",
225
  "single_word": false,
226
  "lstrip": false,
227
  "rstrip": false,
228
+ "normalized": false,
229
+ "special": true
230
  },
231
  {
232
  "id": 32022,
 
233
  "content": "<extra_id_77>",
234
  "single_word": false,
235
  "lstrip": false,
236
  "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
  },
240
  {
241
  "id": 32023,
 
242
  "content": "<extra_id_76>",
243
  "single_word": false,
244
  "lstrip": false,
245
  "rstrip": false,
246
+ "normalized": false,
247
+ "special": true
248
  },
249
  {
250
  "id": 32024,
 
251
  "content": "<extra_id_75>",
252
  "single_word": false,
253
  "lstrip": false,
254
  "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
  },
258
  {
259
  "id": 32025,
 
260
  "content": "<extra_id_74>",
261
  "single_word": false,
262
  "lstrip": false,
263
  "rstrip": false,
264
+ "normalized": false,
265
+ "special": true
266
  },
267
  {
268
  "id": 32026,
 
269
  "content": "<extra_id_73>",
270
  "single_word": false,
271
  "lstrip": false,
272
  "rstrip": false,
273
+ "normalized": false,
274
+ "special": true
275
  },
276
  {
277
  "id": 32027,
 
278
  "content": "<extra_id_72>",
279
  "single_word": false,
280
  "lstrip": false,
281
  "rstrip": false,
282
+ "normalized": false,
283
+ "special": true
284
  },
285
  {
286
  "id": 32028,
 
287
  "content": "<extra_id_71>",
288
  "single_word": false,
289
  "lstrip": false,
290
  "rstrip": false,
291
+ "normalized": false,
292
+ "special": true
293
  },
294
  {
295
  "id": 32029,
 
296
  "content": "<extra_id_70>",
297
  "single_word": false,
298
  "lstrip": false,
299
  "rstrip": false,
300
+ "normalized": false,
301
+ "special": true
302
  },
303
  {
304
  "id": 32030,
 
305
  "content": "<extra_id_69>",
306
  "single_word": false,
307
  "lstrip": false,
308
  "rstrip": false,
309
+ "normalized": false,
310
+ "special": true
311
  },
312
  {
313
  "id": 32031,
 
314
  "content": "<extra_id_68>",
315
  "single_word": false,
316
  "lstrip": false,
317
  "rstrip": false,
318
+ "normalized": false,
319
+ "special": true
320
  },
321
  {
322
  "id": 32032,
 
323
  "content": "<extra_id_67>",
324
  "single_word": false,
325
  "lstrip": false,
326
  "rstrip": false,
327
+ "normalized": false,
328
+ "special": true
329
  },
330
  {
331
  "id": 32033,
 
332
  "content": "<extra_id_66>",
333
  "single_word": false,
334
  "lstrip": false,
335
  "rstrip": false,
336
+ "normalized": false,
337
+ "special": true
338
  },
339
  {
340
  "id": 32034,
 
341
  "content": "<extra_id_65>",
342
  "single_word": false,
343
  "lstrip": false,
344
  "rstrip": false,
345
+ "normalized": false,
346
+ "special": true
347
  },
348
  {
349
  "id": 32035,
 
350
  "content": "<extra_id_64>",
351
  "single_word": false,
352
  "lstrip": false,
353
  "rstrip": false,
354
+ "normalized": false,
355
+ "special": true
356
  },
357
  {
358
  "id": 32036,
 
359
  "content": "<extra_id_63>",
360
  "single_word": false,
361
  "lstrip": false,
362
  "rstrip": false,
363
+ "normalized": false,
364
+ "special": true
365
  },
366
  {
367
  "id": 32037,
 
368
  "content": "<extra_id_62>",
369
  "single_word": false,
370
  "lstrip": false,
371
  "rstrip": false,
372
+ "normalized": false,
373
+ "special": true
374
  },
375
  {
376
  "id": 32038,
 
377
  "content": "<extra_id_61>",
378
  "single_word": false,
379
  "lstrip": false,
380
  "rstrip": false,
381
+ "normalized": false,
382
+ "special": true
383
  },
384
  {
385
  "id": 32039,
 
386
  "content": "<extra_id_60>",
387
  "single_word": false,
388
  "lstrip": false,
389
  "rstrip": false,
390
+ "normalized": false,
391
+ "special": true
392
  },
393
  {
394
  "id": 32040,
 
395
  "content": "<extra_id_59>",
396
  "single_word": false,
397
  "lstrip": false,
398
  "rstrip": false,
399
+ "normalized": false,
400
+ "special": true
401
  },
402
  {
403
  "id": 32041,
 
404
  "content": "<extra_id_58>",
405
  "single_word": false,
406
  "lstrip": false,
407
  "rstrip": false,
408
+ "normalized": false,
409
+ "special": true
410
  },
411
  {
412
  "id": 32042,
 
413
  "content": "<extra_id_57>",
414
  "single_word": false,
415
  "lstrip": false,
416
  "rstrip": false,
417
+ "normalized": false,
418
+ "special": true
419
  },
420
  {
421
  "id": 32043,
 
422
  "content": "<extra_id_56>",
423
  "single_word": false,
424
  "lstrip": false,
425
  "rstrip": false,
426
+ "normalized": false,
427
+ "special": true
428
  },
429
  {
430
  "id": 32044,
 
431
  "content": "<extra_id_55>",
432
  "single_word": false,
433
  "lstrip": false,
434
  "rstrip": false,
435
+ "normalized": false,
436
+ "special": true
437
  },
438
  {
439
  "id": 32045,
 
440
  "content": "<extra_id_54>",
441
  "single_word": false,
442
  "lstrip": false,
443
  "rstrip": false,
444
+ "normalized": false,
445
+ "special": true
446
  },
447
  {
448
  "id": 32046,
 
449
  "content": "<extra_id_53>",
450
  "single_word": false,
451
  "lstrip": false,
452
  "rstrip": false,
453
+ "normalized": false,
454
+ "special": true
455
  },
456
  {
457
  "id": 32047,
 
458
  "content": "<extra_id_52>",
459
  "single_word": false,
460
  "lstrip": false,
461
  "rstrip": false,
462
+ "normalized": false,
463
+ "special": true
464
  },
465
  {
466
  "id": 32048,
 
467
  "content": "<extra_id_51>",
468
  "single_word": false,
469
  "lstrip": false,
470
  "rstrip": false,
471
+ "normalized": false,
472
+ "special": true
473
  },
474
  {
475
  "id": 32049,
 
476
  "content": "<extra_id_50>",
477
  "single_word": false,
478
  "lstrip": false,
479
  "rstrip": false,
480
+ "normalized": false,
481
+ "special": true
482
  },
483
  {
484
  "id": 32050,
 
485
  "content": "<extra_id_49>",
486
  "single_word": false,
487
  "lstrip": false,
488
  "rstrip": false,
489
+ "normalized": false,
490
+ "special": true
491
  },
492
  {
493
  "id": 32051,
 
494
  "content": "<extra_id_48>",
495
  "single_word": false,
496
  "lstrip": false,
497
  "rstrip": false,
498
+ "normalized": false,
499
+ "special": true
500
  },
501
  {
502
  "id": 32052,
 
503
  "content": "<extra_id_47>",
504
  "single_word": false,
505
  "lstrip": false,
506
  "rstrip": false,
507
+ "normalized": false,
508
+ "special": true
509
  },
510
  {
511
  "id": 32053,
 
512
  "content": "<extra_id_46>",
513
  "single_word": false,
514
  "lstrip": false,
515
  "rstrip": false,
516
+ "normalized": false,
517
+ "special": true
518
  },
519
  {
520
  "id": 32054,
 
521
  "content": "<extra_id_45>",
522
  "single_word": false,
523
  "lstrip": false,
524
  "rstrip": false,
525
+ "normalized": false,
526
+ "special": true
527
  },
528
  {
529
  "id": 32055,
 
530
  "content": "<extra_id_44>",
531
  "single_word": false,
532
  "lstrip": false,
533
  "rstrip": false,
534
+ "normalized": false,
535
+ "special": true
536
  },
537
  {
538
  "id": 32056,
 
539
  "content": "<extra_id_43>",
540
  "single_word": false,
541
  "lstrip": false,
542
  "rstrip": false,
543
+ "normalized": false,
544
+ "special": true
545
  },
546
  {
547
  "id": 32057,
 
548
  "content": "<extra_id_42>",
549
  "single_word": false,
550
  "lstrip": false,
551
  "rstrip": false,
552
+ "normalized": false,
553
+ "special": true
554
  },
555
  {
556
  "id": 32058,
 
557
  "content": "<extra_id_41>",
558
  "single_word": false,
559
  "lstrip": false,
560
  "rstrip": false,
561
+ "normalized": false,
562
+ "special": true
563
  },
564
  {
565
  "id": 32059,
 
566
  "content": "<extra_id_40>",
567
  "single_word": false,
568
  "lstrip": false,
569
  "rstrip": false,
570
+ "normalized": false,
571
+ "special": true
572
  },
573
  {
574
  "id": 32060,
 
575
  "content": "<extra_id_39>",
576
  "single_word": false,
577
  "lstrip": false,
578
  "rstrip": false,
579
+ "normalized": false,
580
+ "special": true
581
  },
582
  {
583
  "id": 32061,
 
584
  "content": "<extra_id_38>",
585
  "single_word": false,
586
  "lstrip": false,
587
  "rstrip": false,
588
+ "normalized": false,
589
+ "special": true
590
  },
591
  {
592
  "id": 32062,
 
593
  "content": "<extra_id_37>",
594
  "single_word": false,
595
  "lstrip": false,
596
  "rstrip": false,
597
+ "normalized": false,
598
+ "special": true
599
  },
600
  {
601
  "id": 32063,
 
602
  "content": "<extra_id_36>",
603
  "single_word": false,
604
  "lstrip": false,
605
  "rstrip": false,
606
+ "normalized": false,
607
+ "special": true
608
  },
609
  {
610
  "id": 32064,
 
611
  "content": "<extra_id_35>",
612
  "single_word": false,
613
  "lstrip": false,
614
  "rstrip": false,
615
+ "normalized": false,
616
+ "special": true
617
  },
618
  {
619
  "id": 32065,
 
620
  "content": "<extra_id_34>",
621
  "single_word": false,
622
  "lstrip": false,
623
  "rstrip": false,
624
+ "normalized": false,
625
+ "special": true
626
  },
627
  {
628
  "id": 32066,
 
629
  "content": "<extra_id_33>",
630
  "single_word": false,
631
  "lstrip": false,
632
  "rstrip": false,
633
+ "normalized": false,
634
+ "special": true
635
  },
636
  {
637
  "id": 32067,
 
638
  "content": "<extra_id_32>",
639
  "single_word": false,
640
  "lstrip": false,
641
  "rstrip": false,
642
+ "normalized": false,
643
+ "special": true
644
  },
645
  {
646
  "id": 32068,
 
647
  "content": "<extra_id_31>",
648
  "single_word": false,
649
  "lstrip": false,
650
  "rstrip": false,
651
+ "normalized": false,
652
+ "special": true
653
  },
654
  {
655
  "id": 32069,
 
656
  "content": "<extra_id_30>",
657
  "single_word": false,
658
  "lstrip": false,
659
  "rstrip": false,
660
+ "normalized": false,
661
+ "special": true
662
  },
663
  {
664
  "id": 32070,
 
665
  "content": "<extra_id_29>",
666
  "single_word": false,
667
  "lstrip": false,
668
  "rstrip": false,
669
+ "normalized": false,
670
+ "special": true
671
  },
672
  {
673
  "id": 32071,
 
674
  "content": "<extra_id_28>",
675
  "single_word": false,
676
  "lstrip": false,
677
  "rstrip": false,
678
+ "normalized": false,
679
+ "special": true
680
  },
681
  {
682
  "id": 32072,
 
683
  "content": "<extra_id_27>",
684
  "single_word": false,
685
  "lstrip": false,
686
  "rstrip": false,
687
+ "normalized": false,
688
+ "special": true
689
  },
690
  {
691
  "id": 32073,
 
692
  "content": "<extra_id_26>",
693
  "single_word": false,
694
  "lstrip": false,
695
  "rstrip": false,
696
+ "normalized": false,
697
+ "special": true
698
  },
699
  {
700
  "id": 32074,
 
701
  "content": "<extra_id_25>",
702
  "single_word": false,
703
  "lstrip": false,
704
  "rstrip": false,
705
+ "normalized": false,
706
+ "special": true
707
  },
708
  {
709
  "id": 32075,
 
710
  "content": "<extra_id_24>",
711
  "single_word": false,
712
  "lstrip": false,
713
  "rstrip": false,
714
+ "normalized": false,
715
+ "special": true
716
  },
717
  {
718
  "id": 32076,
 
719
  "content": "<extra_id_23>",
720
  "single_word": false,
721
  "lstrip": false,
722
  "rstrip": false,
723
+ "normalized": false,
724
+ "special": true
725
  },
726
  {
727
  "id": 32077,
 
728
  "content": "<extra_id_22>",
729
  "single_word": false,
730
  "lstrip": false,
731
  "rstrip": false,
732
+ "normalized": false,
733
+ "special": true
734
  },
735
  {
736
  "id": 32078,
 
737
  "content": "<extra_id_21>",
738
  "single_word": false,
739
  "lstrip": false,
740
  "rstrip": false,
741
+ "normalized": false,
742
+ "special": true
743
  },
744
  {
745
  "id": 32079,
 
746
  "content": "<extra_id_20>",
747
  "single_word": false,
748
  "lstrip": false,
749
  "rstrip": false,
750
+ "normalized": false,
751
+ "special": true
752
  },
753
  {
754
  "id": 32080,
 
755
  "content": "<extra_id_19>",
756
  "single_word": false,
757
  "lstrip": false,
758
  "rstrip": false,
759
+ "normalized": false,
760
+ "special": true
761
  },
762
  {
763
  "id": 32081,
 
764
  "content": "<extra_id_18>",
765
  "single_word": false,
766
  "lstrip": false,
767
  "rstrip": false,
768
+ "normalized": false,
769
+ "special": true
770
  },
771
  {
772
  "id": 32082,
 
773
  "content": "<extra_id_17>",
774
  "single_word": false,
775
  "lstrip": false,
776
  "rstrip": false,
777
+ "normalized": false,
778
+ "special": true
779
  },
780
  {
781
  "id": 32083,
 
782
  "content": "<extra_id_16>",
783
  "single_word": false,
784
  "lstrip": false,
785
  "rstrip": false,
786
+ "normalized": false,
787
+ "special": true
788
  },
789
  {
790
  "id": 32084,
 
791
  "content": "<extra_id_15>",
792
  "single_word": false,
793
  "lstrip": false,
794
  "rstrip": false,
795
+ "normalized": false,
796
+ "special": true
797
  },
798
  {
799
  "id": 32085,
 
800
  "content": "<extra_id_14>",
801
  "single_word": false,
802
  "lstrip": false,
803
  "rstrip": false,
804
+ "normalized": false,
805
+ "special": true
806
  },
807
  {
808
  "id": 32086,
 
809
  "content": "<extra_id_13>",
810
  "single_word": false,
811
  "lstrip": false,
812
  "rstrip": false,
813
+ "normalized": false,
814
+ "special": true
815
  },
816
  {
817
  "id": 32087,
 
818
  "content": "<extra_id_12>",
819
  "single_word": false,
820
  "lstrip": false,
821
  "rstrip": false,
822
+ "normalized": false,
823
+ "special": true
824
  },
825
  {
826
  "id": 32088,
 
827
  "content": "<extra_id_11>",
828
  "single_word": false,
829
  "lstrip": false,
830
  "rstrip": false,
831
+ "normalized": false,
832
+ "special": true
833
  },
834
  {
835
  "id": 32089,
 
836
  "content": "<extra_id_10>",
837
  "single_word": false,
838
  "lstrip": false,
839
  "rstrip": false,
840
+ "normalized": false,
841
+ "special": true
842
  },
843
  {
844
  "id": 32090,
 
845
  "content": "<extra_id_9>",
846
  "single_word": false,
847
  "lstrip": false,
848
  "rstrip": false,
849
+ "normalized": false,
850
+ "special": true
851
  },
852
  {
853
  "id": 32091,
 
854
  "content": "<extra_id_8>",
855
  "single_word": false,
856
  "lstrip": false,
857
  "rstrip": false,
858
+ "normalized": false,
859
+ "special": true
860
  },
861
  {
862
  "id": 32092,
 
863
  "content": "<extra_id_7>",
864
  "single_word": false,
865
  "lstrip": false,
866
  "rstrip": false,
867
+ "normalized": false,
868
+ "special": true
869
  },
870
  {
871
  "id": 32093,
 
872
  "content": "<extra_id_6>",
873
  "single_word": false,
874
  "lstrip": false,
875
  "rstrip": false,
876
+ "normalized": false,
877
+ "special": true
878
  },
879
  {
880
  "id": 32094,
 
881
  "content": "<extra_id_5>",
882
  "single_word": false,
883
  "lstrip": false,
884
  "rstrip": false,
885
+ "normalized": false,
886
+ "special": true
887
  },
888
  {
889
  "id": 32095,
 
890
  "content": "<extra_id_4>",
891
  "single_word": false,
892
  "lstrip": false,
893
  "rstrip": false,
894
+ "normalized": false,
895
+ "special": true
896
  },
897
  {
898
  "id": 32096,
 
899
  "content": "<extra_id_3>",
900
  "single_word": false,
901
  "lstrip": false,
902
  "rstrip": false,
903
+ "normalized": false,
904
+ "special": true
905
  },
906
  {
907
  "id": 32097,
 
908
  "content": "<extra_id_2>",
909
  "single_word": false,
910
  "lstrip": false,
911
  "rstrip": false,
912
+ "normalized": false,
913
+ "special": true
914
  },
915
  {
916
  "id": 32098,
 
917
  "content": "<extra_id_1>",
918
  "single_word": false,
919
  "lstrip": false,
920
  "rstrip": false,
921
+ "normalized": false,
922
+ "special": true
923
  },
924
  {
925
  "id": 32099,
 
926
  "content": "<extra_id_0>",
927
  "single_word": false,
928
  "lstrip": false,
929
  "rstrip": false,
930
+ "normalized": false,
931
+ "special": true
932
  }
933
  ],
934
  "normalizer": {
tokenizer_config.json CHANGED
@@ -1 +1,112 @@
1
- {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "truncation_side": "left", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-small", "tokenizer_class": "T5Tokenizer"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
105
+ "extra_ids": 100,
106
+ "name_or_path": "/zhangpai23/zhuqi/pre-trained-models/t5-small",
107
+ "pad_token": "<pad>",
108
+ "special_tokens_map_file": null,
109
+ "tokenizer_class": "T5Tokenizer",
110
+ "truncation_side": "left",
111
+ "unk_token": "<unk>"
112
+ }