Wesamalnabki-bsc commited on
Commit
3a0c8fb
·
verified ·
1 Parent(s): a5be852

Push model using huggingface_hub.

Browse files
added_tokens.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
- "<<ENT>>": 250103,
3
- "<<SEP>>": 250104,
4
- "[FLERT]": 250102,
5
- "[MASK]": 250101
6
  }
 
1
  {
2
+ "<<ENT>>": 128002,
3
+ "<<SEP>>": 128003,
4
+ "[FLERT]": 128001,
5
+ "[MASK]": 128000
6
  }
gliner_config.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "class_token_index": 250103,
3
  "dropout": 0.4,
4
  "embed_ent_token": true,
5
  "encoder_config": {
6
  "_attn_implementation_autoset": false,
7
- "_name_or_path": "microsoft/mdeberta-v3-base",
8
  "add_cross_attention": false,
9
  "architectures": null,
10
  "attention_probs_dropout_prob": 0.1,
@@ -25,13 +25,13 @@
25
  "forced_eos_token_id": null,
26
  "hidden_act": "gelu",
27
  "hidden_dropout_prob": 0.1,
28
- "hidden_size": 768,
29
  "id2label": {
30
  "0": "LABEL_0",
31
  "1": "LABEL_1"
32
  },
33
  "initializer_range": 0.02,
34
- "intermediate_size": 3072,
35
  "is_decoder": false,
36
  "is_encoder_decoder": false,
37
  "label2id": {
@@ -48,10 +48,10 @@
48
  "model_type": "deberta-v2",
49
  "no_repeat_ngram_size": 0,
50
  "norm_rel_ebd": "layer_norm",
51
- "num_attention_heads": 12,
52
  "num_beam_groups": 1,
53
  "num_beams": 1,
54
- "num_hidden_layers": 12,
55
  "num_return_sequences": 1,
56
  "output_attentions": false,
57
  "output_hidden_states": false,
@@ -59,7 +59,7 @@
59
  "pad_token_id": 0,
60
  "pooler_dropout": 0,
61
  "pooler_hidden_act": "gelu",
62
- "pooler_hidden_size": 768,
63
  "pos_att_type": [
64
  "p2c",
65
  "c2p"
@@ -90,37 +90,42 @@
90
  "type_vocab_size": 0,
91
  "typical_p": 1.0,
92
  "use_bfloat16": false,
93
- "vocab_size": 250105
94
  },
95
  "ent_token": "<<ENT>>",
96
- "eval_every": 5000,
97
  "fine_tune": true,
98
  "fuse_layers": false,
 
99
  "has_rnn": true,
100
- "hidden_size": 512,
101
  "labels_encoder": null,
102
  "labels_encoder_config": null,
 
103
  "lr_encoder": "1e-5",
104
  "lr_others": "5e-5",
105
- "max_len": 768,
106
  "max_neg_type_ratio": 1,
107
  "max_types": 25,
108
- "max_width": 12,
109
- "model_name": "microsoft/mdeberta-v3-base",
110
  "model_type": "gliner",
111
- "name": "correct",
112
  "num_post_fusion_layers": 1,
113
- "num_steps": 30000,
114
  "post_fusion_schema": "",
 
115
  "random_drop": true,
 
116
  "sep_token": "<<SEP>>",
117
  "shuffle_types": true,
118
  "size_sup": -1,
119
- "span_mode": "markerV0",
120
  "subtoken_pooling": "first",
121
- "train_batch_size": 8,
 
122
  "transformers_version": "4.48.3",
123
- "vocab_size": 250105,
124
- "warmup_ratio": 3000,
125
  "words_splitter_type": "whitespace"
126
  }
 
1
  {
2
+ "class_token_index": 128002,
3
  "dropout": 0.4,
4
  "embed_ent_token": true,
5
  "encoder_config": {
6
  "_attn_implementation_autoset": false,
7
+ "_name_or_path": "microsoft/deberta-v3-large",
8
  "add_cross_attention": false,
9
  "architectures": null,
10
  "attention_probs_dropout_prob": 0.1,
 
25
  "forced_eos_token_id": null,
26
  "hidden_act": "gelu",
27
  "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 1024,
29
  "id2label": {
30
  "0": "LABEL_0",
31
  "1": "LABEL_1"
32
  },
33
  "initializer_range": 0.02,
34
+ "intermediate_size": 4096,
35
  "is_decoder": false,
36
  "is_encoder_decoder": false,
37
  "label2id": {
 
48
  "model_type": "deberta-v2",
49
  "no_repeat_ngram_size": 0,
50
  "norm_rel_ebd": "layer_norm",
51
+ "num_attention_heads": 16,
52
  "num_beam_groups": 1,
53
  "num_beams": 1,
54
+ "num_hidden_layers": 24,
55
  "num_return_sequences": 1,
56
  "output_attentions": false,
57
  "output_hidden_states": false,
 
59
  "pad_token_id": 0,
60
  "pooler_dropout": 0,
61
  "pooler_hidden_act": "gelu",
62
+ "pooler_hidden_size": 1024,
63
  "pos_att_type": [
64
  "p2c",
65
  "c2p"
 
90
  "type_vocab_size": 0,
91
  "typical_p": 1.0,
92
  "use_bfloat16": false,
93
+ "vocab_size": 128004
94
  },
95
  "ent_token": "<<ENT>>",
96
+ "eval_every": 2500,
97
  "fine_tune": true,
98
  "fuse_layers": false,
99
+ "gradient_accumulation_steps": 2,
100
  "has_rnn": true,
101
+ "hidden_size": 768,
102
  "labels_encoder": null,
103
  "labels_encoder_config": null,
104
+ "log_dir": "logs",
105
  "lr_encoder": "1e-5",
106
  "lr_others": "5e-5",
107
+ "max_len": 384,
108
  "max_neg_type_ratio": 1,
109
  "max_types": 25,
110
+ "max_width": 1,
111
+ "model_name": "microsoft/deberta-v3-large",
112
  "model_type": "gliner",
113
+ "name": "large",
114
  "num_post_fusion_layers": 1,
115
+ "num_steps": 60000,
116
  "post_fusion_schema": "",
117
+ "prev_path": "none",
118
  "random_drop": true,
119
+ "root_dir": "ablation_backbone",
120
  "sep_token": "<<SEP>>",
121
  "shuffle_types": true,
122
  "size_sup": -1,
123
+ "span_mode": "marker",
124
  "subtoken_pooling": "first",
125
+ "train_batch_size": 4,
126
+ "train_data": "NuMinds_custom_data_mix.json",
127
  "transformers_version": "4.48.3",
128
+ "vocab_size": 128004,
129
+ "warmup_ratio": 0.1,
130
  "words_splitter_type": "whitespace"
131
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc220bd9d01f44987a553d6dc855e684526dca149c8cecdd125aa249ba404cfd
3
- size 1155879086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c6fc56939820b78fda03d7dd5766055c6ca792e335743ef685564a446de6fb
3
+ size 1795640934
spm.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
3
- size 4305025
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d81efd0311d8d5900181604ebe2b6216b7f7f0dd1e209cf69a42bfbed21b97a
3
- size 16351471
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dba35d5dbe252aeafc5330bb2c1dbccd1632c829ea62a142b4082179db3fd94
3
+ size 8657331
tokenizer_config.json CHANGED
@@ -32,807 +32,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "250001": {
36
- "content": "▁<extra_id_99>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": false
42
- },
43
- "250002": {
44
- "content": "▁<extra_id_98>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": false
50
- },
51
- "250003": {
52
- "content": "▁<extra_id_97>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": false
58
- },
59
- "250004": {
60
- "content": "▁<extra_id_96>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": false
66
- },
67
- "250005": {
68
- "content": "▁<extra_id_95>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": false
74
- },
75
- "250006": {
76
- "content": "▁<extra_id_94>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": false
82
- },
83
- "250007": {
84
- "content": "▁<extra_id_93>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": false
90
- },
91
- "250008": {
92
- "content": "▁<extra_id_92>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": false
98
- },
99
- "250009": {
100
- "content": "▁<extra_id_91>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": false
106
- },
107
- "250010": {
108
- "content": "▁<extra_id_90>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": false
114
- },
115
- "250011": {
116
- "content": "▁<extra_id_89>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": false
122
- },
123
- "250012": {
124
- "content": "▁<extra_id_88>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": false
130
- },
131
- "250013": {
132
- "content": "▁<extra_id_87>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": false
138
- },
139
- "250014": {
140
- "content": "▁<extra_id_86>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": false
146
- },
147
- "250015": {
148
- "content": "▁<extra_id_85>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": false
154
- },
155
- "250016": {
156
- "content": "▁<extra_id_84>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": false
162
- },
163
- "250017": {
164
- "content": "▁<extra_id_83>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": false
170
- },
171
- "250018": {
172
- "content": "▁<extra_id_82>",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": false
178
- },
179
- "250019": {
180
- "content": "▁<extra_id_81>",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": false
186
- },
187
- "250020": {
188
- "content": "▁<extra_id_80>",
189
- "lstrip": false,
190
- "normalized": false,
191
- "rstrip": false,
192
- "single_word": false,
193
- "special": false
194
- },
195
- "250021": {
196
- "content": "▁<extra_id_79>",
197
- "lstrip": false,
198
- "normalized": false,
199
- "rstrip": false,
200
- "single_word": false,
201
- "special": false
202
- },
203
- "250022": {
204
- "content": "▁<extra_id_78>",
205
- "lstrip": false,
206
- "normalized": false,
207
- "rstrip": false,
208
- "single_word": false,
209
- "special": false
210
- },
211
- "250023": {
212
- "content": "▁<extra_id_77>",
213
- "lstrip": false,
214
- "normalized": false,
215
- "rstrip": false,
216
- "single_word": false,
217
- "special": false
218
- },
219
- "250024": {
220
- "content": "▁<extra_id_76>",
221
- "lstrip": false,
222
- "normalized": false,
223
- "rstrip": false,
224
- "single_word": false,
225
- "special": false
226
- },
227
- "250025": {
228
- "content": "▁<extra_id_75>",
229
- "lstrip": false,
230
- "normalized": false,
231
- "rstrip": false,
232
- "single_word": false,
233
- "special": false
234
- },
235
- "250026": {
236
- "content": "▁<extra_id_74>",
237
- "lstrip": false,
238
- "normalized": false,
239
- "rstrip": false,
240
- "single_word": false,
241
- "special": false
242
- },
243
- "250027": {
244
- "content": "▁<extra_id_73>",
245
- "lstrip": false,
246
- "normalized": false,
247
- "rstrip": false,
248
- "single_word": false,
249
- "special": false
250
- },
251
- "250028": {
252
- "content": "▁<extra_id_72>",
253
- "lstrip": false,
254
- "normalized": false,
255
- "rstrip": false,
256
- "single_word": false,
257
- "special": false
258
- },
259
- "250029": {
260
- "content": "▁<extra_id_71>",
261
- "lstrip": false,
262
- "normalized": false,
263
- "rstrip": false,
264
- "single_word": false,
265
- "special": false
266
- },
267
- "250030": {
268
- "content": "▁<extra_id_70>",
269
- "lstrip": false,
270
- "normalized": false,
271
- "rstrip": false,
272
- "single_word": false,
273
- "special": false
274
- },
275
- "250031": {
276
- "content": "▁<extra_id_69>",
277
- "lstrip": false,
278
- "normalized": false,
279
- "rstrip": false,
280
- "single_word": false,
281
- "special": false
282
- },
283
- "250032": {
284
- "content": "▁<extra_id_68>",
285
- "lstrip": false,
286
- "normalized": false,
287
- "rstrip": false,
288
- "single_word": false,
289
- "special": false
290
- },
291
- "250033": {
292
- "content": "▁<extra_id_67>",
293
- "lstrip": false,
294
- "normalized": false,
295
- "rstrip": false,
296
- "single_word": false,
297
- "special": false
298
- },
299
- "250034": {
300
- "content": "▁<extra_id_66>",
301
- "lstrip": false,
302
- "normalized": false,
303
- "rstrip": false,
304
- "single_word": false,
305
- "special": false
306
- },
307
- "250035": {
308
- "content": "▁<extra_id_65>",
309
- "lstrip": false,
310
- "normalized": false,
311
- "rstrip": false,
312
- "single_word": false,
313
- "special": false
314
- },
315
- "250036": {
316
- "content": "▁<extra_id_64>",
317
- "lstrip": false,
318
- "normalized": false,
319
- "rstrip": false,
320
- "single_word": false,
321
- "special": false
322
- },
323
- "250037": {
324
- "content": "▁<extra_id_63>",
325
- "lstrip": false,
326
- "normalized": false,
327
- "rstrip": false,
328
- "single_word": false,
329
- "special": false
330
- },
331
- "250038": {
332
- "content": "▁<extra_id_62>",
333
- "lstrip": false,
334
- "normalized": false,
335
- "rstrip": false,
336
- "single_word": false,
337
- "special": false
338
- },
339
- "250039": {
340
- "content": "▁<extra_id_61>",
341
- "lstrip": false,
342
- "normalized": false,
343
- "rstrip": false,
344
- "single_word": false,
345
- "special": false
346
- },
347
- "250040": {
348
- "content": "▁<extra_id_60>",
349
- "lstrip": false,
350
- "normalized": false,
351
- "rstrip": false,
352
- "single_word": false,
353
- "special": false
354
- },
355
- "250041": {
356
- "content": "▁<extra_id_59>",
357
- "lstrip": false,
358
- "normalized": false,
359
- "rstrip": false,
360
- "single_word": false,
361
- "special": false
362
- },
363
- "250042": {
364
- "content": "▁<extra_id_58>",
365
- "lstrip": false,
366
- "normalized": false,
367
- "rstrip": false,
368
- "single_word": false,
369
- "special": false
370
- },
371
- "250043": {
372
- "content": "▁<extra_id_57>",
373
- "lstrip": false,
374
- "normalized": false,
375
- "rstrip": false,
376
- "single_word": false,
377
- "special": false
378
- },
379
- "250044": {
380
- "content": "▁<extra_id_56>",
381
- "lstrip": false,
382
- "normalized": false,
383
- "rstrip": false,
384
- "single_word": false,
385
- "special": false
386
- },
387
- "250045": {
388
- "content": "▁<extra_id_55>",
389
- "lstrip": false,
390
- "normalized": false,
391
- "rstrip": false,
392
- "single_word": false,
393
- "special": false
394
- },
395
- "250046": {
396
- "content": "▁<extra_id_54>",
397
- "lstrip": false,
398
- "normalized": false,
399
- "rstrip": false,
400
- "single_word": false,
401
- "special": false
402
- },
403
- "250047": {
404
- "content": "▁<extra_id_53>",
405
- "lstrip": false,
406
- "normalized": false,
407
- "rstrip": false,
408
- "single_word": false,
409
- "special": false
410
- },
411
- "250048": {
412
- "content": "▁<extra_id_52>",
413
- "lstrip": false,
414
- "normalized": false,
415
- "rstrip": false,
416
- "single_word": false,
417
- "special": false
418
- },
419
- "250049": {
420
- "content": "▁<extra_id_51>",
421
- "lstrip": false,
422
- "normalized": false,
423
- "rstrip": false,
424
- "single_word": false,
425
- "special": false
426
- },
427
- "250050": {
428
- "content": "▁<extra_id_50>",
429
- "lstrip": false,
430
- "normalized": false,
431
- "rstrip": false,
432
- "single_word": false,
433
- "special": false
434
- },
435
- "250051": {
436
- "content": "▁<extra_id_49>",
437
- "lstrip": false,
438
- "normalized": false,
439
- "rstrip": false,
440
- "single_word": false,
441
- "special": false
442
- },
443
- "250052": {
444
- "content": "▁<extra_id_48>",
445
- "lstrip": false,
446
- "normalized": false,
447
- "rstrip": false,
448
- "single_word": false,
449
- "special": false
450
- },
451
- "250053": {
452
- "content": "▁<extra_id_47>",
453
- "lstrip": false,
454
- "normalized": false,
455
- "rstrip": false,
456
- "single_word": false,
457
- "special": false
458
- },
459
- "250054": {
460
- "content": "▁<extra_id_46>",
461
- "lstrip": false,
462
- "normalized": false,
463
- "rstrip": false,
464
- "single_word": false,
465
- "special": false
466
- },
467
- "250055": {
468
- "content": "▁<extra_id_45>",
469
- "lstrip": false,
470
- "normalized": false,
471
- "rstrip": false,
472
- "single_word": false,
473
- "special": false
474
- },
475
- "250056": {
476
- "content": "▁<extra_id_44>",
477
- "lstrip": false,
478
- "normalized": false,
479
- "rstrip": false,
480
- "single_word": false,
481
- "special": false
482
- },
483
- "250057": {
484
- "content": "▁<extra_id_43>",
485
- "lstrip": false,
486
- "normalized": false,
487
- "rstrip": false,
488
- "single_word": false,
489
- "special": false
490
- },
491
- "250058": {
492
- "content": "▁<extra_id_42>",
493
- "lstrip": false,
494
- "normalized": false,
495
- "rstrip": false,
496
- "single_word": false,
497
- "special": false
498
- },
499
- "250059": {
500
- "content": "▁<extra_id_41>",
501
- "lstrip": false,
502
- "normalized": false,
503
- "rstrip": false,
504
- "single_word": false,
505
- "special": false
506
- },
507
- "250060": {
508
- "content": "▁<extra_id_40>",
509
- "lstrip": false,
510
- "normalized": false,
511
- "rstrip": false,
512
- "single_word": false,
513
- "special": false
514
- },
515
- "250061": {
516
- "content": "▁<extra_id_39>",
517
- "lstrip": false,
518
- "normalized": false,
519
- "rstrip": false,
520
- "single_word": false,
521
- "special": false
522
- },
523
- "250062": {
524
- "content": "▁<extra_id_38>",
525
- "lstrip": false,
526
- "normalized": false,
527
- "rstrip": false,
528
- "single_word": false,
529
- "special": false
530
- },
531
- "250063": {
532
- "content": "▁<extra_id_37>",
533
- "lstrip": false,
534
- "normalized": false,
535
- "rstrip": false,
536
- "single_word": false,
537
- "special": false
538
- },
539
- "250064": {
540
- "content": "▁<extra_id_36>",
541
- "lstrip": false,
542
- "normalized": false,
543
- "rstrip": false,
544
- "single_word": false,
545
- "special": false
546
- },
547
- "250065": {
548
- "content": "▁<extra_id_35>",
549
- "lstrip": false,
550
- "normalized": false,
551
- "rstrip": false,
552
- "single_word": false,
553
- "special": false
554
- },
555
- "250066": {
556
- "content": "▁<extra_id_34>",
557
- "lstrip": false,
558
- "normalized": false,
559
- "rstrip": false,
560
- "single_word": false,
561
- "special": false
562
- },
563
- "250067": {
564
- "content": "▁<extra_id_33>",
565
- "lstrip": false,
566
- "normalized": false,
567
- "rstrip": false,
568
- "single_word": false,
569
- "special": false
570
- },
571
- "250068": {
572
- "content": "▁<extra_id_32>",
573
- "lstrip": false,
574
- "normalized": false,
575
- "rstrip": false,
576
- "single_word": false,
577
- "special": false
578
- },
579
- "250069": {
580
- "content": "▁<extra_id_31>",
581
- "lstrip": false,
582
- "normalized": false,
583
- "rstrip": false,
584
- "single_word": false,
585
- "special": false
586
- },
587
- "250070": {
588
- "content": "▁<extra_id_30>",
589
- "lstrip": false,
590
- "normalized": false,
591
- "rstrip": false,
592
- "single_word": false,
593
- "special": false
594
- },
595
- "250071": {
596
- "content": "▁<extra_id_29>",
597
- "lstrip": false,
598
- "normalized": false,
599
- "rstrip": false,
600
- "single_word": false,
601
- "special": false
602
- },
603
- "250072": {
604
- "content": "▁<extra_id_28>",
605
- "lstrip": false,
606
- "normalized": false,
607
- "rstrip": false,
608
- "single_word": false,
609
- "special": false
610
- },
611
- "250073": {
612
- "content": "▁<extra_id_27>",
613
- "lstrip": false,
614
- "normalized": false,
615
- "rstrip": false,
616
- "single_word": false,
617
- "special": false
618
- },
619
- "250074": {
620
- "content": "▁<extra_id_26>",
621
- "lstrip": false,
622
- "normalized": false,
623
- "rstrip": false,
624
- "single_word": false,
625
- "special": false
626
- },
627
- "250075": {
628
- "content": "▁<extra_id_25>",
629
- "lstrip": false,
630
- "normalized": false,
631
- "rstrip": false,
632
- "single_word": false,
633
- "special": false
634
- },
635
- "250076": {
636
- "content": "▁<extra_id_24>",
637
- "lstrip": false,
638
- "normalized": false,
639
- "rstrip": false,
640
- "single_word": false,
641
- "special": false
642
- },
643
- "250077": {
644
- "content": "▁<extra_id_23>",
645
- "lstrip": false,
646
- "normalized": false,
647
- "rstrip": false,
648
- "single_word": false,
649
- "special": false
650
- },
651
- "250078": {
652
- "content": "▁<extra_id_22>",
653
- "lstrip": false,
654
- "normalized": false,
655
- "rstrip": false,
656
- "single_word": false,
657
- "special": false
658
- },
659
- "250079": {
660
- "content": "▁<extra_id_21>",
661
- "lstrip": false,
662
- "normalized": false,
663
- "rstrip": false,
664
- "single_word": false,
665
- "special": false
666
- },
667
- "250080": {
668
- "content": "▁<extra_id_20>",
669
- "lstrip": false,
670
- "normalized": false,
671
- "rstrip": false,
672
- "single_word": false,
673
- "special": false
674
- },
675
- "250081": {
676
- "content": "▁<extra_id_19>",
677
- "lstrip": false,
678
- "normalized": false,
679
- "rstrip": false,
680
- "single_word": false,
681
- "special": false
682
- },
683
- "250082": {
684
- "content": "▁<extra_id_18>",
685
- "lstrip": false,
686
- "normalized": false,
687
- "rstrip": false,
688
- "single_word": false,
689
- "special": false
690
- },
691
- "250083": {
692
- "content": "▁<extra_id_17>",
693
- "lstrip": false,
694
- "normalized": false,
695
- "rstrip": false,
696
- "single_word": false,
697
- "special": false
698
- },
699
- "250084": {
700
- "content": "▁<extra_id_16>",
701
- "lstrip": false,
702
- "normalized": false,
703
- "rstrip": false,
704
- "single_word": false,
705
- "special": false
706
- },
707
- "250085": {
708
- "content": "▁<extra_id_15>",
709
- "lstrip": false,
710
- "normalized": false,
711
- "rstrip": false,
712
- "single_word": false,
713
- "special": false
714
- },
715
- "250086": {
716
- "content": "▁<extra_id_14>",
717
- "lstrip": false,
718
- "normalized": false,
719
- "rstrip": false,
720
- "single_word": false,
721
- "special": false
722
- },
723
- "250087": {
724
- "content": "▁<extra_id_13>",
725
- "lstrip": false,
726
- "normalized": false,
727
- "rstrip": false,
728
- "single_word": false,
729
- "special": false
730
- },
731
- "250088": {
732
- "content": "▁<extra_id_12>",
733
- "lstrip": false,
734
- "normalized": false,
735
- "rstrip": false,
736
- "single_word": false,
737
- "special": false
738
- },
739
- "250089": {
740
- "content": "▁<extra_id_11>",
741
- "lstrip": false,
742
- "normalized": false,
743
- "rstrip": false,
744
- "single_word": false,
745
- "special": false
746
- },
747
- "250090": {
748
- "content": "▁<extra_id_10>",
749
- "lstrip": false,
750
- "normalized": false,
751
- "rstrip": false,
752
- "single_word": false,
753
- "special": false
754
- },
755
- "250091": {
756
- "content": "▁<extra_id_9>",
757
- "lstrip": false,
758
- "normalized": false,
759
- "rstrip": false,
760
- "single_word": false,
761
- "special": false
762
- },
763
- "250092": {
764
- "content": "▁<extra_id_8>",
765
- "lstrip": false,
766
- "normalized": false,
767
- "rstrip": false,
768
- "single_word": false,
769
- "special": false
770
- },
771
- "250093": {
772
- "content": "▁<extra_id_7>",
773
- "lstrip": false,
774
- "normalized": false,
775
- "rstrip": false,
776
- "single_word": false,
777
- "special": false
778
- },
779
- "250094": {
780
- "content": "▁<extra_id_6>",
781
- "lstrip": false,
782
- "normalized": false,
783
- "rstrip": false,
784
- "single_word": false,
785
- "special": false
786
- },
787
- "250095": {
788
- "content": "▁<extra_id_5>",
789
- "lstrip": false,
790
- "normalized": false,
791
- "rstrip": false,
792
- "single_word": false,
793
- "special": false
794
- },
795
- "250096": {
796
- "content": "▁<extra_id_4>",
797
- "lstrip": false,
798
- "normalized": false,
799
- "rstrip": false,
800
- "single_word": false,
801
- "special": false
802
- },
803
- "250097": {
804
- "content": "▁<extra_id_3>",
805
- "lstrip": false,
806
- "normalized": false,
807
- "rstrip": false,
808
- "single_word": false,
809
- "special": false
810
- },
811
- "250098": {
812
- "content": "▁<extra_id_2>",
813
- "lstrip": false,
814
- "normalized": false,
815
- "rstrip": false,
816
- "single_word": false,
817
- "special": false
818
- },
819
- "250099": {
820
- "content": "▁<extra_id_1>",
821
- "lstrip": false,
822
- "normalized": false,
823
- "rstrip": false,
824
- "single_word": false,
825
- "special": false
826
- },
827
- "250100": {
828
- "content": "▁<extra_id_0>",
829
- "lstrip": false,
830
- "normalized": false,
831
- "rstrip": false,
832
- "single_word": false,
833
- "special": false
834
- },
835
- "250101": {
836
  "content": "[MASK]",
837
  "lstrip": false,
838
  "normalized": false,
@@ -840,7 +40,7 @@
840
  "single_word": false,
841
  "special": true
842
  },
843
- "250102": {
844
  "content": "[FLERT]",
845
  "lstrip": false,
846
  "normalized": true,
@@ -848,7 +48,7 @@
848
  "single_word": false,
849
  "special": false
850
  },
851
- "250103": {
852
  "content": "<<ENT>>",
853
  "lstrip": false,
854
  "normalized": true,
@@ -856,7 +56,7 @@
856
  "single_word": false,
857
  "special": false
858
  },
859
- "250104": {
860
  "content": "<<SEP>>",
861
  "lstrip": false,
862
  "normalized": true,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "128000": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
40
  "single_word": false,
41
  "special": true
42
  },
43
+ "128001": {
44
  "content": "[FLERT]",
45
  "lstrip": false,
46
  "normalized": true,
 
48
  "single_word": false,
49
  "special": false
50
  },
51
+ "128002": {
52
  "content": "<<ENT>>",
53
  "lstrip": false,
54
  "normalized": true,
 
56
  "single_word": false,
57
  "special": false
58
  },
59
+ "128003": {
60
  "content": "<<SEP>>",
61
  "lstrip": false,
62
  "normalized": true,