guihu commited on
Commit
2ec841c
1 Parent(s): 52c46ef

Upload DeBERTa L weights

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,1077 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sileod/deberta-v3-large-tasksource-nli",
3
+ "architectures": [
4
+ "DebertaV2ForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifiers_size": [
8
+ 3,
9
+ 2,
10
+ 2,
11
+ 2,
12
+ 2,
13
+ 2,
14
+ 1,
15
+ 2,
16
+ 3,
17
+ 2,
18
+ 2,
19
+ 2,
20
+ 3,
21
+ 3,
22
+ 3,
23
+ 3,
24
+ 1,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2,
29
+ 3,
30
+ 2,
31
+ 2,
32
+ 2,
33
+ 6,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2,
38
+ 2,
39
+ 2,
40
+ 2,
41
+ 3,
42
+ 3,
43
+ 3,
44
+ 3,
45
+ 3,
46
+ 3,
47
+ 3,
48
+ 2,
49
+ 2,
50
+ 2,
51
+ 2,
52
+ 5,
53
+ 3,
54
+ 3,
55
+ 3,
56
+ 3,
57
+ 3,
58
+ 3,
59
+ 3,
60
+ 3,
61
+ 2,
62
+ 2,
63
+ 2,
64
+ 3,
65
+ 3,
66
+ 3,
67
+ 3,
68
+ 3,
69
+ 3,
70
+ 3,
71
+ 3,
72
+ 2,
73
+ 2,
74
+ 2,
75
+ 2,
76
+ 47,
77
+ 23,
78
+ 9,
79
+ 1,
80
+ 1,
81
+ 1,
82
+ 1,
83
+ 1,
84
+ 1,
85
+ 1,
86
+ 1,
87
+ 1,
88
+ 1,
89
+ 1,
90
+ 1,
91
+ 1,
92
+ 1,
93
+ 1,
94
+ 1,
95
+ 1,
96
+ 1,
97
+ 1,
98
+ 1,
99
+ 1,
100
+ 1,
101
+ 1,
102
+ 1,
103
+ 1,
104
+ 1,
105
+ 1,
106
+ 1,
107
+ 1,
108
+ 1,
109
+ 1,
110
+ 1,
111
+ 1,
112
+ 1,
113
+ 1,
114
+ 1,
115
+ 1,
116
+ 1,
117
+ 1,
118
+ 1,
119
+ 1,
120
+ 1,
121
+ 1,
122
+ 1,
123
+ 1,
124
+ 1,
125
+ 1,
126
+ 1,
127
+ 1,
128
+ 1,
129
+ 1,
130
+ 1,
131
+ 1,
132
+ 1,
133
+ 1,
134
+ 1,
135
+ 1,
136
+ 1,
137
+ 1,
138
+ 1,
139
+ 1,
140
+ 1,
141
+ 1,
142
+ 1,
143
+ 1,
144
+ 1,
145
+ 1,
146
+ 1,
147
+ 1,
148
+ 1,
149
+ 1,
150
+ 1,
151
+ 1,
152
+ 1,
153
+ 1,
154
+ 1,
155
+ 1,
156
+ 1,
157
+ 1,
158
+ 1,
159
+ 1,
160
+ 1,
161
+ 1,
162
+ 1,
163
+ 1,
164
+ 1,
165
+ 1,
166
+ 1,
167
+ 1,
168
+ 1,
169
+ 1,
170
+ 1,
171
+ 1,
172
+ 1,
173
+ 1,
174
+ 1,
175
+ 1,
176
+ 1,
177
+ 1,
178
+ 1,
179
+ 1,
180
+ 1,
181
+ 1,
182
+ 1,
183
+ 1,
184
+ 1,
185
+ 1,
186
+ 1,
187
+ 1,
188
+ 1,
189
+ 1,
190
+ 1,
191
+ 1,
192
+ 1,
193
+ 1,
194
+ 1,
195
+ 1,
196
+ 1,
197
+ 1,
198
+ 1,
199
+ 1,
200
+ 1,
201
+ 1,
202
+ 1,
203
+ 1,
204
+ 1,
205
+ 1,
206
+ 1,
207
+ 2,
208
+ 2,
209
+ 2,
210
+ 2,
211
+ 2,
212
+ 2,
213
+ 20,
214
+ 50,
215
+ 3,
216
+ 3,
217
+ 4,
218
+ 2,
219
+ 8,
220
+ 3,
221
+ 2,
222
+ 20,
223
+ 4,
224
+ 2,
225
+ 2,
226
+ 3,
227
+ 3,
228
+ 3,
229
+ 3,
230
+ 3,
231
+ 174,
232
+ 2,
233
+ 41,
234
+ 51,
235
+ 3,
236
+ 2,
237
+ 2,
238
+ 2,
239
+ 2,
240
+ 2,
241
+ 3,
242
+ 2,
243
+ 3,
244
+ 16,
245
+ 2,
246
+ 2,
247
+ 2,
248
+ 8,
249
+ 18,
250
+ 2,
251
+ 17,
252
+ 42,
253
+ 7,
254
+ 3,
255
+ 12,
256
+ 7,
257
+ 4,
258
+ 11,
259
+ 3,
260
+ 100,
261
+ 13,
262
+ 100,
263
+ 8,
264
+ 1,
265
+ 20,
266
+ 2,
267
+ 2,
268
+ 4,
269
+ 5,
270
+ 3,
271
+ 4,
272
+ 14,
273
+ 2,
274
+ 6,
275
+ 4,
276
+ 2,
277
+ 1,
278
+ 3,
279
+ 10,
280
+ 3,
281
+ 10,
282
+ 4,
283
+ 2,
284
+ 7,
285
+ 6,
286
+ 28,
287
+ 3,
288
+ 6,
289
+ 5,
290
+ 7,
291
+ 3,
292
+ 6,
293
+ 4,
294
+ 2,
295
+ 7,
296
+ 2,
297
+ 2,
298
+ 2,
299
+ 2,
300
+ 6,
301
+ 20,
302
+ 2,
303
+ 9,
304
+ 13,
305
+ 4,
306
+ 3,
307
+ 3,
308
+ 2,
309
+ 4,
310
+ 2,
311
+ 2,
312
+ 2,
313
+ 2,
314
+ 2,
315
+ 2,
316
+ 4,
317
+ 1,
318
+ 2,
319
+ 1,
320
+ 13,
321
+ 3,
322
+ 5,
323
+ 11,
324
+ 37,
325
+ 2,
326
+ 49,
327
+ 40,
328
+ 10,
329
+ 4,
330
+ 1,
331
+ 2,
332
+ 2,
333
+ 1,
334
+ 5,
335
+ 2,
336
+ 3,
337
+ 2,
338
+ 2,
339
+ 12,
340
+ 3,
341
+ 3,
342
+ 2,
343
+ 19,
344
+ 3,
345
+ 1,
346
+ 2,
347
+ 2,
348
+ 2,
349
+ 2,
350
+ 2,
351
+ 1,
352
+ 2,
353
+ 2,
354
+ 1,
355
+ 1,
356
+ 2,
357
+ 3,
358
+ 2,
359
+ 1,
360
+ 4,
361
+ 3,
362
+ 1,
363
+ 1,
364
+ 1,
365
+ 2,
366
+ 3,
367
+ 2,
368
+ 3,
369
+ 1,
370
+ 1,
371
+ 2,
372
+ 1,
373
+ 3,
374
+ 2,
375
+ 2,
376
+ 2,
377
+ 2,
378
+ 2,
379
+ 3,
380
+ 2,
381
+ 2,
382
+ 2,
383
+ 1,
384
+ 3,
385
+ 2,
386
+ 2,
387
+ 1,
388
+ 1,
389
+ 1,
390
+ 1,
391
+ 2,
392
+ 1,
393
+ 1,
394
+ 1,
395
+ 1,
396
+ 4,
397
+ 1,
398
+ 1,
399
+ 1,
400
+ 1,
401
+ 3,
402
+ 1,
403
+ 3,
404
+ 1,
405
+ 2,
406
+ 2,
407
+ 1,
408
+ 2,
409
+ 3,
410
+ 3,
411
+ 2,
412
+ 1,
413
+ 3,
414
+ 1,
415
+ 1,
416
+ 3,
417
+ 1,
418
+ 3,
419
+ 2,
420
+ 1,
421
+ 1,
422
+ 1,
423
+ 2,
424
+ 50,
425
+ 50,
426
+ 50,
427
+ 50,
428
+ 2,
429
+ 1,
430
+ 1,
431
+ 1,
432
+ 1,
433
+ 1,
434
+ 1,
435
+ 1,
436
+ 1,
437
+ 1,
438
+ 1,
439
+ 2,
440
+ 2,
441
+ 2,
442
+ 2,
443
+ 77,
444
+ 1,
445
+ 3,
446
+ 2,
447
+ 2,
448
+ 1,
449
+ 1,
450
+ 2,
451
+ 2,
452
+ 2,
453
+ 2,
454
+ 2,
455
+ 2,
456
+ 2,
457
+ 2,
458
+ 2,
459
+ 3,
460
+ 18,
461
+ 13,
462
+ 2,
463
+ 2,
464
+ 2,
465
+ 2,
466
+ 2,
467
+ 2,
468
+ 4,
469
+ 2,
470
+ 24,
471
+ 23,
472
+ 67,
473
+ 279,
474
+ 3,
475
+ 2,
476
+ 2,
477
+ 1,
478
+ 2,
479
+ 2,
480
+ 3,
481
+ 1,
482
+ 2,
483
+ 3,
484
+ 2,
485
+ 3,
486
+ 3,
487
+ 2,
488
+ 2,
489
+ 4,
490
+ 1,
491
+ 17,
492
+ 3,
493
+ 2,
494
+ 3,
495
+ 2,
496
+ 3,
497
+ 3,
498
+ 2,
499
+ 1,
500
+ 1,
501
+ 3,
502
+ 2,
503
+ 9,
504
+ 2,
505
+ 1,
506
+ 1,
507
+ 1,
508
+ 1,
509
+ 1,
510
+ 2,
511
+ 2,
512
+ 3,
513
+ 2,
514
+ 3,
515
+ 4,
516
+ 2,
517
+ 3,
518
+ 3,
519
+ 3,
520
+ 1,
521
+ 1
522
+ ],
523
+ "hidden_act": "gelu",
524
+ "hidden_dropout_prob": 0.1,
525
+ "hidden_size": 1024,
526
+ "id2label": {
527
+ "0": "entailment",
528
+ "1": "neutral",
529
+ "2": "contradiction"
530
+ },
531
+ "initializer_range": 0.02,
532
+ "intermediate_size": 4096,
533
+ "label2id": {
534
+ "contradiction": 2,
535
+ "entailment": 0,
536
+ "neutral": 1
537
+ },
538
+ "layer_norm_eps": 1e-07,
539
+ "max_position_embeddings": 512,
540
+ "max_relative_positions": -1,
541
+ "model_type": "deberta-v2",
542
+ "norm_rel_ebd": "layer_norm",
543
+ "num_attention_heads": 16,
544
+ "num_hidden_layers": 24,
545
+ "pad_token_id": 0,
546
+ "pooler_dropout": 0,
547
+ "pooler_hidden_act": "gelu",
548
+ "pooler_hidden_size": 1024,
549
+ "pos_att_type": [
550
+ "p2c",
551
+ "c2p"
552
+ ],
553
+ "position_biased_input": false,
554
+ "position_buckets": 256,
555
+ "relative_attention": true,
556
+ "share_att_key": true,
557
+ "tasks": [
558
+ "glue/mnli",
559
+ "glue/qnli",
560
+ "glue/rte",
561
+ "glue/wnli",
562
+ "glue/mrpc",
563
+ "glue/qqp",
564
+ "glue/stsb",
565
+ "super_glue/boolq",
566
+ "super_glue/cb",
567
+ "super_glue/multirc",
568
+ "super_glue/wic",
569
+ "super_glue/axg",
570
+ "anli/a1",
571
+ "anli/a2",
572
+ "anli/a3",
573
+ "sick/label",
574
+ "sick/relatedness",
575
+ "sick/entailment_AB",
576
+ "snli",
577
+ "scitail/snli_format",
578
+ "hans",
579
+ "WANLI",
580
+ "recast/recast_megaveridicality",
581
+ "recast/recast_sentiment",
582
+ "recast/recast_verbnet",
583
+ "recast/recast_kg_relations",
584
+ "recast/recast_puns",
585
+ "recast/recast_factuality",
586
+ "recast/recast_verbcorner",
587
+ "recast/recast_ner",
588
+ "probability_words_nli/usnli",
589
+ "probability_words_nli/reasoning_1hop",
590
+ "probability_words_nli/reasoning_2hop",
591
+ "nan-nli/joey234--nan-nli",
592
+ "nli_fever",
593
+ "breaking_nli",
594
+ "conj_nli",
595
+ "fracas",
596
+ "dialogue_nli",
597
+ "mpe",
598
+ "dnc",
599
+ "recast_white/fnplus",
600
+ "recast_white/sprl",
601
+ "recast_white/dpr",
602
+ "joci",
603
+ "robust_nli/IS_CS",
604
+ "robust_nli/LI_LI",
605
+ "robust_nli/ST_WO",
606
+ "robust_nli/PI_SP",
607
+ "robust_nli/PI_CD",
608
+ "robust_nli/ST_SE",
609
+ "robust_nli/ST_NE",
610
+ "robust_nli/ST_LM",
611
+ "robust_nli_is_sd",
612
+ "robust_nli_li_ts",
613
+ "add_one_rte",
614
+ "imppres/implicature_gradable_adjective/log",
615
+ "imppres/implicature_numerals_2_3/log",
616
+ "imppres/implicature_modals/log",
617
+ "imppres/implicature_gradable_verb/log",
618
+ "imppres/implicature_numerals_10_100/log",
619
+ "imppres/implicature_quantifiers/log",
620
+ "imppres/implicature_connectives/log",
621
+ "glue_diagnostics/diagnostics",
622
+ "hlgd",
623
+ "paws/labeled_final",
624
+ "paws/labeled_swap",
625
+ "medical_questions_pairs",
626
+ "conll2003/pos_tags",
627
+ "conll2003/chunk_tags",
628
+ "conll2003/ner_tags",
629
+ "model-written-evals",
630
+ "truthful_qa/multiple_choice",
631
+ "fig-qa",
632
+ "bigbench/tracking_shuffled_objects",
633
+ "bigbench/color",
634
+ "bigbench/cause_and_effect",
635
+ "bigbench/dyck_languages",
636
+ "bigbench/identify_math_theorems",
637
+ "bigbench/unit_interpretation",
638
+ "bigbench/arithmetic",
639
+ "bigbench/social_iqa",
640
+ "bigbench/penguins_in_a_table",
641
+ "bigbench/play_dialog_same_or_different",
642
+ "bigbench/novel_concepts",
643
+ "bigbench/international_phonetic_alphabet_nli",
644
+ "bigbench/implicatures",
645
+ "bigbench/english_proverbs",
646
+ "bigbench/simple_ethical_questions",
647
+ "bigbench/sports_understanding",
648
+ "bigbench/emoji_movie",
649
+ "bigbench/implicit_relations",
650
+ "bigbench/empirical_judgments",
651
+ "bigbench/navigate",
652
+ "bigbench/logical_deduction",
653
+ "bigbench/reasoning_about_colored_objects",
654
+ "bigbench/snarks",
655
+ "bigbench/gre_reading_comprehension",
656
+ "bigbench/ruin_names",
657
+ "bigbench/analytic_entailment",
658
+ "bigbench/authorship_verification",
659
+ "bigbench/code_line_description",
660
+ "bigbench/logical_sequence",
661
+ "bigbench/disambiguation_qa",
662
+ "bigbench/misconceptions",
663
+ "bigbench/understanding_fables",
664
+ "bigbench/intent_recognition",
665
+ "bigbench/odd_one_out",
666
+ "bigbench/temporal_sequences",
667
+ "bigbench/analogical_similarity",
668
+ "bigbench/emojis_emotion_prediction",
669
+ "bigbench/key_value_maps",
670
+ "bigbench/identify_odd_metaphor",
671
+ "bigbench/geometric_shapes",
672
+ "bigbench/suicide_risk",
673
+ "bigbench/strategyqa",
674
+ "bigbench/logical_fallacy_detection",
675
+ "bigbench/known_unknowns",
676
+ "bigbench/social_support",
677
+ "bigbench/logic_grid_puzzle",
678
+ "bigbench/question_selection",
679
+ "bigbench/fact_checker",
680
+ "bigbench/moral_permissibility",
681
+ "bigbench/dark_humor_detection",
682
+ "bigbench/mathematical_induction",
683
+ "bigbench/movie_recommendation",
684
+ "bigbench/human_organs_senses",
685
+ "bigbench/vitaminc_fact_verification",
686
+ "bigbench/movie_dialog_same_or_different",
687
+ "bigbench/metaphor_boolean",
688
+ "bigbench/causal_judgment",
689
+ "bigbench/epistemic_reasoning",
690
+ "bigbench/sentence_ambiguity",
691
+ "bigbench/logical_args",
692
+ "bigbench/hindu_knowledge",
693
+ "bigbench/cs_algorithms",
694
+ "bigbench/hhh_alignment",
695
+ "bigbench/physical_intuition",
696
+ "bigbench/crash_blossom",
697
+ "bigbench/cifar10_classification",
698
+ "bigbench/riddle_sense",
699
+ "bigbench/hyperbaton",
700
+ "bigbench/general_knowledge",
701
+ "bigbench/anachronisms",
702
+ "bigbench/entailed_polarity",
703
+ "bigbench/nonsense_words_grammar",
704
+ "bigbench/mnist_ascii",
705
+ "bigbench/symbol_interpretation",
706
+ "bigbench/figure_of_speech_detection",
707
+ "bigbench/abstract_narrative_understanding",
708
+ "bigbench/irony_identification",
709
+ "bigbench/discourse_marker_prediction",
710
+ "bigbench/date_understanding",
711
+ "bigbench/metaphor_understanding",
712
+ "bigbench/goal_step_wikihow",
713
+ "bigbench/similarities_abstraction",
714
+ "bigbench/salient_translation_error_detection",
715
+ "bigbench/formal_fallacies_syllogisms_negation",
716
+ "bigbench/presuppositions_as_nli",
717
+ "bigbench/fantasy_reasoning",
718
+ "bigbench/contextual_parametric_knowledge_conflicts",
719
+ "bigbench/evaluating_information_essentiality",
720
+ "bigbench/real_or_fake_text",
721
+ "bigbench/conceptual_combinations",
722
+ "bigbench/phrase_relatedness",
723
+ "bigbench/crass_ai",
724
+ "bigbench/undo_permutation",
725
+ "bigbench/physics",
726
+ "bigbench/timedial",
727
+ "bigbench/winowhy",
728
+ "bigbench/checkmate_in_one",
729
+ "bigbench/bbq_lite_json",
730
+ "bigbench/strange_stories",
731
+ "bigbench/elementary_math_qa",
732
+ "cos_e/v1.0",
733
+ "cosmos_qa",
734
+ "dream",
735
+ "openbookqa",
736
+ "qasc",
737
+ "quartz",
738
+ "quail",
739
+ "head_qa/en",
740
+ "sciq",
741
+ "social_i_qa",
742
+ "wiki_hop/original",
743
+ "wiqa",
744
+ "piqa",
745
+ "hellaswag",
746
+ "super_glue/copa",
747
+ "balanced-copa",
748
+ "e-CARE",
749
+ "art",
750
+ "winogrande/winogrande_xl",
751
+ "codah/codah",
752
+ "ai2_arc/ARC-Challenge/challenge",
753
+ "ai2_arc/ARC-Easy/challenge",
754
+ "definite_pronoun_resolution",
755
+ "swag/regular",
756
+ "math_qa",
757
+ "glue/cola",
758
+ "glue/sst2",
759
+ "utilitarianism",
760
+ "amazon_counterfactual/en",
761
+ "insincere-questions",
762
+ "toxic_conversations",
763
+ "TuringBench",
764
+ "trec",
765
+ "vitaminc/tals--vitaminc",
766
+ "hope_edi/english",
767
+ "rumoureval_2019/RumourEval2019",
768
+ "ethos/binary",
769
+ "ethos/multilabel",
770
+ "tweet_eval/sentiment",
771
+ "tweet_eval/offensive",
772
+ "tweet_eval/emoji",
773
+ "tweet_eval/emotion",
774
+ "tweet_eval/irony",
775
+ "tweet_eval/hate",
776
+ "tweet_eval/stance_abortion",
777
+ "tweet_eval/stance_atheism",
778
+ "tweet_eval/stance_climate",
779
+ "tweet_eval/stance_feminist",
780
+ "tweet_eval/stance_hillary",
781
+ "discovery/discovery",
782
+ "pragmeval/squinky-informativeness",
783
+ "pragmeval/switchboard",
784
+ "pragmeval/mrda",
785
+ "pragmeval/verifiability",
786
+ "pragmeval/emobank-arousal",
787
+ "pragmeval/emobank-dominance",
788
+ "pragmeval/squinky-formality",
789
+ "pragmeval/squinky-implicature",
790
+ "pragmeval/emobank-valence",
791
+ "pragmeval/persuasiveness-claimtype",
792
+ "pragmeval/persuasiveness-eloquence",
793
+ "pragmeval/emergent",
794
+ "pragmeval/pdtb",
795
+ "pragmeval/persuasiveness-strength",
796
+ "pragmeval/persuasiveness-relevance",
797
+ "pragmeval/persuasiveness-specificity",
798
+ "pragmeval/persuasiveness-premisetype",
799
+ "pragmeval/stac",
800
+ "pragmeval/sarcasm",
801
+ "pragmeval/gum",
802
+ "silicone/oasis",
803
+ "silicone/meld_e",
804
+ "silicone/meld_s",
805
+ "silicone/maptask",
806
+ "silicone/dyda_e",
807
+ "silicone/dyda_da",
808
+ "silicone/iemocap",
809
+ "silicone/sem",
810
+ "lex_glue/eurlex",
811
+ "lex_glue/scotus",
812
+ "lex_glue/ledgar",
813
+ "lex_glue/unfair_tos",
814
+ "lex_glue/case_hold",
815
+ "language-identification",
816
+ "imdb",
817
+ "rotten_tomatoes",
818
+ "ag_news",
819
+ "yelp_review_full/yelp_review_full",
820
+ "financial_phrasebank/sentences_allagree",
821
+ "poem_sentiment",
822
+ "dbpedia_14/dbpedia_14",
823
+ "amazon_polarity/amazon_polarity",
824
+ "app_reviews",
825
+ "hate_speech18",
826
+ "sms_spam",
827
+ "humicroedit/subtask-1",
828
+ "humicroedit/subtask-2",
829
+ "snips_built_in_intents",
830
+ "hate_speech_offensive",
831
+ "yahoo_answers_topics",
832
+ "stackoverflow-questions",
833
+ "hyperpartisan_news",
834
+ "sciie",
835
+ "citation_intent",
836
+ "go_emotions/simplified",
837
+ "scicite",
838
+ "liar",
839
+ "lexical_relation_classification/CogALexV",
840
+ "lexical_relation_classification/EVALution",
841
+ "lexical_relation_classification/ROOT09",
842
+ "lexical_relation_classification/BLESS",
843
+ "lexical_relation_classification/K&H+N",
844
+ "linguisticprobing/odd_man_out",
845
+ "linguisticprobing/tree_depth",
846
+ "linguisticprobing/coordination_inversion",
847
+ "linguisticprobing/obj_number",
848
+ "linguisticprobing/bigram_shift",
849
+ "linguisticprobing/past_present",
850
+ "linguisticprobing/sentence_length",
851
+ "linguisticprobing/top_constituents",
852
+ "linguisticprobing/subj_number",
853
+ "crowdflower/political-media-message",
854
+ "crowdflower/text_emotion",
855
+ "crowdflower/corporate-messaging",
856
+ "crowdflower/economic-news",
857
+ "crowdflower/airline-sentiment",
858
+ "crowdflower/tweet_global_warming",
859
+ "crowdflower/sentiment_nuclear_power",
860
+ "crowdflower/political-media-audience",
861
+ "crowdflower/political-media-bias",
862
+ "ethics/commonsense",
863
+ "ethics/deontology",
864
+ "ethics/justice",
865
+ "ethics/virtue",
866
+ "emo/emo2019",
867
+ "google_wellformed_query",
868
+ "tweets_hate_speech_detection",
869
+ "has_part",
870
+ "wnut_17/wnut_17",
871
+ "ncbi_disease/ncbi_disease",
872
+ "acronym_identification",
873
+ "jnlpba/jnlpba",
874
+ "ontonotes_english/SpeedOfMagic--ontonotes_english",
875
+ "blog_authorship_corpus/gender",
876
+ "blog_authorship_corpus/age",
877
+ "blog_authorship_corpus/job",
878
+ "open_question_type",
879
+ "health_fact",
880
+ "commonsense_qa",
881
+ "mc_taco",
882
+ "ade_corpus_v2/Ade_corpus_v2_classification",
883
+ "discosense",
884
+ "circa",
885
+ "phrase_similarity",
886
+ "scientific-exaggeration-detection",
887
+ "quarel",
888
+ "fever-evidence-related/mwong--fever-related",
889
+ "numer_sense",
890
+ "dynasent/dynabench.dynasent.r1.all/r1",
891
+ "dynasent/dynabench.dynasent.r2.all/r2",
892
+ "Sarcasm_News_Headline",
893
+ "sem_eval_2010_task_8",
894
+ "auditor_review/demo-org--auditor_review",
895
+ "medmcqa",
896
+ "Dynasent_Disagreement",
897
+ "Politeness_Disagreement",
898
+ "SBIC_Disagreement",
899
+ "SChem_Disagreement",
900
+ "Dilemmas_Disagreement",
901
+ "logiqa",
902
+ "wiki_qa",
903
+ "cycic_classification",
904
+ "cycic_multiplechoice",
905
+ "sts-companion",
906
+ "commonsense_qa_2.0",
907
+ "lingnli",
908
+ "monotonicity-entailment",
909
+ "arct",
910
+ "scinli",
911
+ "naturallogic",
912
+ "onestop_qa",
913
+ "moral_stories/full",
914
+ "prost",
915
+ "dynahate",
916
+ "syntactic-augmentation-nli",
917
+ "autotnli",
918
+ "CONDAQA",
919
+ "webgpt_comparisons",
920
+ "synthetic-instruct-gptj-pairwise",
921
+ "scruples",
922
+ "wouldyourather",
923
+ "attempto-nli",
924
+ "defeasible-nli/atomic",
925
+ "defeasible-nli/snli",
926
+ "help-nli",
927
+ "nli-veridicality-transitivity",
928
+ "natural-language-satisfiability",
929
+ "lonli",
930
+ "dadc-limit-nli",
931
+ "FLUTE",
932
+ "strategy-qa",
933
+ "summarize_from_feedback/comparisons",
934
+ "folio",
935
+ "tomi-nli",
936
+ "avicenna",
937
+ "SHP",
938
+ "MedQA-USMLE-4-options-hf",
939
+ "wikimedqa/medwiki",
940
+ "cicero",
941
+ "CREAK",
942
+ "mutual",
943
+ "NeQA",
944
+ "quote-repetition",
945
+ "redefine-math",
946
+ "puzzte",
947
+ "implicatures",
948
+ "race/middle",
949
+ "race/high",
950
+ "race-c",
951
+ "spartqa-yn",
952
+ "spartqa-mchoice",
953
+ "temporal-nli",
954
+ "riddle_sense",
955
+ "clcd-english",
956
+ "twentyquestions",
957
+ "reclor",
958
+ "counterfactually-augmented-imdb",
959
+ "counterfactually-augmented-snli",
960
+ "cnli",
961
+ "boolq-natural-perturbations",
962
+ "acceptability-prediction",
963
+ "equate",
964
+ "ScienceQA_text_only",
965
+ "ekar_english",
966
+ "implicit-hate-stg1",
967
+ "chaos-mnli-ambiguity",
968
+ "headline_cause/en_simple",
969
+ "logiqa-2.0-nli",
970
+ "oasst2_dense_flat/quality",
971
+ "oasst2_dense_flat/toxicity",
972
+ "oasst2_dense_flat/helpfulness",
973
+ "mindgames",
974
+ "universal_dependencies/en_partut/deprel",
975
+ "universal_dependencies/en_lines/deprel",
976
+ "universal_dependencies/en_ewt/deprel",
977
+ "universal_dependencies/en_gum/deprel",
978
+ "ambient",
979
+ "path-naturalness-prediction",
980
+ "civil_comments/toxicity",
981
+ "civil_comments/severe_toxicity",
982
+ "civil_comments/obscene",
983
+ "civil_comments/threat",
984
+ "civil_comments/insult",
985
+ "civil_comments/identity_attack",
986
+ "civil_comments/sexual_explicit",
987
+ "cloth",
988
+ "dgen",
989
+ "I2D2",
990
+ "args_me",
991
+ "Touche23-ValueEval",
992
+ "starcon",
993
+ "banking77",
994
+ "lsat_qa/all",
995
+ "ConTRoL-nli",
996
+ "tracie",
997
+ "sherliic",
998
+ "sen-making/1",
999
+ "sen-making/2",
1000
+ "winowhy",
1001
+ "mbib-base/cognitive-bias",
1002
+ "mbib-base/fake-news",
1003
+ "mbib-base/gender-bias",
1004
+ "mbib-base/hate-speech",
1005
+ "mbib-base/linguistic-bias",
1006
+ "mbib-base/political-bias",
1007
+ "mbib-base/racial-bias",
1008
+ "mbib-base/text-level-bias",
1009
+ "robustLR",
1010
+ "v1/gen_train234_test2to10",
1011
+ "logical-fallacy",
1012
+ "parade",
1013
+ "cladder",
1014
+ "subjectivity",
1015
+ "MOH",
1016
+ "VUAC",
1017
+ "TroFi",
1018
+ "sharc_modified/mod",
1019
+ "conceptrules_v2",
1020
+ "disrpt/eng.dep.scidtb.rels",
1021
+ "conll2000",
1022
+ "few-nerd/supervised",
1023
+ "finer-139",
1024
+ "zero-shot-label-nli",
1025
+ "com2sense",
1026
+ "scone",
1027
+ "winodict",
1028
+ "fool-me-twice",
1029
+ "monli",
1030
+ "corr2cause",
1031
+ "lsat_qa/all",
1032
+ "apt",
1033
+ "twitter-financial-news-sentiment",
1034
+ "icl-symbol-tuning-instruct",
1035
+ "SpaceNLI",
1036
+ "propsegment/nli",
1037
+ "HatemojiBuild",
1038
+ "regset",
1039
+ "esci",
1040
+ "chatbot_arena_conversations",
1041
+ "dnd_style_intents",
1042
+ "FLD.v2",
1043
+ "SDOH-NLI",
1044
+ "scifact_entailment",
1045
+ "feasibilityQA",
1046
+ "simple_pair",
1047
+ "AdjectiveScaleProbe-nli",
1048
+ "resnli",
1049
+ "SpaRTUN",
1050
+ "ReSQ",
1051
+ "semantic_fragments_nli",
1052
+ "dataset_train_nli",
1053
+ "stepgame",
1054
+ "nlgraph",
1055
+ "oasst2_pairwise_rlhf_reward",
1056
+ "hh-rlhf/helpful-online",
1057
+ "hh-rlhf/helpful-base",
1058
+ "hh-rlhf/helpful-rejection-sampled",
1059
+ "hh-rlhf/harmless-base",
1060
+ "ruletaker",
1061
+ "PARARULE-Plus",
1062
+ "proofwriter",
1063
+ "logical-entailment",
1064
+ "nope",
1065
+ "LogicNLI",
1066
+ "babi_nli",
1067
+ "gen_debiased_nli",
1068
+ "imppres/presupposition",
1069
+ "/prag",
1070
+ "blimp-2",
1071
+ "mmlu-4"
1072
+ ],
1073
+ "torch_dtype": "float32",
1074
+ "transformers_version": "4.38.2",
1075
+ "type_vocab_size": 0,
1076
+ "vocab_size": 128100
1077
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:484fb3392bd37f3cf38b07dc6e9d8fa2e6c8b36e9aa420e85d7f705c238665e3
3
+ size 1740308548
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "max_length": 256,
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "pad_to_multiple_of": null,
53
+ "pad_token": "[PAD]",
54
+ "pad_token_type_id": 0,
55
+ "padding_side": "right",
56
+ "sep_token": "[SEP]",
57
+ "sp_model_kwargs": {},
58
+ "split_by_punct": false,
59
+ "stride": 0,
60
+ "tokenizer_class": "DebertaV2Tokenizer",
61
+ "truncation_side": "right",
62
+ "truncation_strategy": "longest_first",
63
+ "unk_token": "[UNK]",
64
+ "vocab_type": "spm"
65
+ }