sileod commited on
Commit
8fecc7c
1 Parent(s): 4ddbff8

Upload DebertaV2ForSequenceClassification

Browse files
Files changed (3) hide show
  1. README.md +18 -20
  2. config.json +240 -204
  3. model.safetensors +3 -0
README.md CHANGED
@@ -1,23 +1,4 @@
1
  ---
2
- license: apache-2.0
3
- language: en
4
- tags:
5
- - deberta-v3-small
6
- - deberta-v3
7
- - deberta
8
- - text-classification
9
- - nli
10
- - natural-language-inference
11
- - multitask
12
- - multi-task
13
- - pipeline
14
- - extreme-multi-task
15
- - extreme-mtl
16
- - tasksource
17
- - zero-shot
18
- - rlhf
19
-
20
-
21
  datasets:
22
  - nyu-mll/glue
23
  - super_glue
@@ -284,10 +265,27 @@ datasets:
284
  - tasksource/regset
285
  - tasksource/babi_nli
286
  - lmsys/chatbot_arena_conversations
 
 
 
287
  metrics:
288
  - accuracy
289
- library_name: transformers
290
  pipeline_tag: zero-shot-classification
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
291
  ---
292
 
293
  # Model Card for DeBERTa-v3-small-tasksource-nli
 
1
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  datasets:
3
  - nyu-mll/glue
4
  - super_glue
 
265
  - tasksource/regset
266
  - tasksource/babi_nli
267
  - lmsys/chatbot_arena_conversations
268
+ language: en
269
+ library_name: transformers
270
+ license: apache-2.0
271
  metrics:
272
  - accuracy
 
273
  pipeline_tag: zero-shot-classification
274
+ tags:
275
+ - deberta-v3-small
276
+ - deberta-v3
277
+ - deberta
278
+ - text-classification
279
+ - nli
280
+ - natural-language-inference
281
+ - multitask
282
+ - multi-task
283
+ - pipeline
284
+ - extreme-multi-task
285
+ - extreme-mtl
286
+ - tasksource
287
+ - zero-shot
288
+ - rlhf
289
  ---
290
 
291
  # Model Card for DeBERTa-v3-small-tasksource-nli
config.json CHANGED
@@ -27,8 +27,8 @@
27
  2,
28
  2,
29
  3,
30
- 6,
31
  2,
 
32
  2,
33
  2,
34
  2,
@@ -68,14 +68,10 @@
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,
@@ -217,12 +213,12 @@
217
  4,
218
  2,
219
  8,
 
220
  3,
221
- 4,
222
  2,
223
  2,
 
224
  20,
225
- 2,
226
  3,
227
  3,
228
  3,
@@ -233,30 +229,30 @@
233
  2,
234
  2,
235
  2,
236
- 2,
237
  41,
 
238
  51,
239
  2,
240
- 3,
241
  2,
242
  2,
243
- 18,
244
  2,
245
  16,
246
- 8,
247
- 3,
248
  17,
249
- 3,
 
250
  2,
251
  2,
 
 
 
 
 
252
  11,
 
 
253
  42,
254
  12,
255
- 7,
256
- 3,
257
  4,
258
- 3,
259
- 7,
260
  100,
261
  13,
262
  100,
@@ -286,28 +282,28 @@
286
  28,
287
  3,
288
  6,
289
- 7,
290
- 6,
291
  5,
 
292
  4,
 
293
  3,
294
  2,
295
- 7,
296
  2,
297
  6,
298
  2,
 
 
299
  2,
300
  2,
301
- 20,
302
  2,
303
  9,
304
  13,
305
  4,
306
  2,
307
- 4,
308
  3,
309
  2,
310
- 2,
311
  3,
312
  2,
313
  2,
@@ -317,11 +313,6 @@
317
  1,
318
  2,
319
  1,
320
- 13,
321
- 3,
322
- 5,
323
- 11,
324
- 37,
325
  2,
326
  49,
327
  40,
@@ -370,8 +361,6 @@
370
  1,
371
  2,
372
  1,
373
- 3,
374
- 2,
375
  2,
376
  2,
377
  2,
@@ -421,10 +410,6 @@
421
  1,
422
  1,
423
  2,
424
- 50,
425
- 50,
426
- 50,
427
- 50,
428
  2,
429
  1,
430
  1,
@@ -441,21 +426,12 @@
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,
@@ -464,13 +440,9 @@
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,
@@ -490,6 +462,7 @@
490
  1,
491
  17,
492
  3,
 
493
  2,
494
  3,
495
  2,
@@ -511,11 +484,56 @@
511
  2,
512
  3,
513
  2,
 
 
 
 
 
 
 
 
 
 
 
514
  2,
515
  3,
516
  3,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
517
  3,
 
518
  1,
 
 
 
 
 
 
519
  1
520
  ],
521
  "hidden_act": "gelu",
@@ -534,7 +552,7 @@
534
  "neutral": 1
535
  },
536
  "layer_norm_eps": 1e-07,
537
- "max_position_embeddings": 512,
538
  "max_relative_positions": -1,
539
  "model_type": "deberta-v2",
540
  "norm_rel_ebd": "layer_norm",
@@ -575,18 +593,18 @@
575
  "scitail/snli_format",
576
  "hans",
577
  "WANLI",
578
- "recast/recast_kg_relations",
579
- "recast/recast_megaveridicality",
580
  "recast/recast_ner",
581
- "recast/recast_verbcorner",
582
- "recast/recast_factuality",
583
- "recast/recast_verbnet",
584
  "recast/recast_puns",
 
585
  "recast/recast_sentiment",
 
 
 
586
  "probability_words_nli/reasoning_2hop",
587
  "probability_words_nli/reasoning_1hop",
588
  "probability_words_nli/usnli",
589
- "nan-nli/joey234--nan-nli",
590
  "nli_fever",
591
  "breaking_nli",
592
  "conj_nli",
@@ -611,122 +629,118 @@
611
  "add_one_rte",
612
  "imppres/implicature_quantifiers/log",
613
  "imppres/implicature_numerals_2_3/log",
614
- "imppres/implicature_modals/log",
615
  "imppres/implicature_gradable_adjective/log",
616
  "imppres/implicature_connectives/log",
 
617
  "imppres/implicature_numerals_10_100/log",
618
  "imppres/implicature_gradable_verb/log",
619
- "glue_diagnostics/diagnostics",
620
  "hlgd",
621
  "paws/labeled_final",
622
  "paws/labeled_swap",
623
  "medical_questions_pairs",
624
- "conll2003/pos_tags",
625
- "conll2003/chunk_tags",
626
- "conll2003/ner_tags",
627
  "model-written-evals",
628
  "truthful_qa/multiple_choice",
629
  "fig-qa",
630
- "bigbench/contextual_parametric_knowledge_conflicts",
631
- "bigbench/empirical_judgments",
632
- "bigbench/hhh_alignment",
633
- "bigbench/metaphor_boolean",
634
- "bigbench/key_value_maps",
635
- "bigbench/known_unknowns",
636
- "bigbench/symbol_interpretation",
637
- "bigbench/misconceptions",
638
  "bigbench/bbq_lite_json",
639
- "bigbench/navigate",
640
- "bigbench/discourse_marker_prediction",
641
- "bigbench/disambiguation_qa",
642
- "bigbench/cifar10_classification",
643
- "bigbench/real_or_fake_text",
644
- "bigbench/moral_permissibility",
645
- "bigbench/abstract_narrative_understanding",
646
- "bigbench/physics",
647
  "bigbench/logical_fallacy_detection",
648
- "bigbench/code_line_description",
649
- "bigbench/implicit_relations",
650
- "bigbench/unit_interpretation",
651
- "bigbench/logical_sequence",
652
  "bigbench/mnist_ascii",
653
- "bigbench/irony_identification",
654
- "bigbench/mathematical_induction",
655
- "bigbench/winowhy",
656
  "bigbench/elementary_math_qa",
657
- "bigbench/implicatures",
658
- "bigbench/vitaminc_fact_verification",
659
- "bigbench/play_dialog_same_or_different",
660
- "bigbench/movie_dialog_same_or_different",
661
- "bigbench/physical_intuition",
662
- "bigbench/reasoning_about_colored_objects",
663
- "bigbench/english_proverbs",
664
- "bigbench/timedial",
665
- "bigbench/conceptual_combinations",
666
- "bigbench/suicide_risk",
667
- "bigbench/movie_recommendation",
668
- "bigbench/formal_fallacies_syllogisms_negation",
669
- "bigbench/causal_judgment",
670
- "bigbench/emoji_movie",
671
  "bigbench/sports_understanding",
672
- "bigbench/hindu_knowledge",
673
- "bigbench/entailed_polarity",
674
- "bigbench/fact_checker",
675
- "bigbench/fantasy_reasoning",
676
- "bigbench/logical_args",
677
- "bigbench/evaluating_information_essentiality",
678
- "bigbench/crass_ai",
679
- "bigbench/identify_odd_metaphor",
680
- "bigbench/cause_and_effect",
681
- "bigbench/undo_permutation",
682
- "bigbench/intent_recognition",
683
- "bigbench/cs_algorithms",
684
- "bigbench/identify_math_theorems",
685
  "bigbench/strategyqa",
686
- "bigbench/penguins_in_a_table",
687
- "bigbench/nonsense_words_grammar",
688
- "bigbench/logical_deduction",
689
- "bigbench/phrase_relatedness",
690
  "bigbench/gre_reading_comprehension",
691
- "bigbench/understanding_fables",
692
- "bigbench/question_selection",
693
- "bigbench/ruin_names",
694
- "bigbench/logic_grid_puzzle",
695
- "bigbench/presuppositions_as_nli",
696
  "bigbench/strange_stories",
697
- "bigbench/general_knowledge",
698
- "bigbench/geometric_shapes",
699
- "bigbench/social_support",
700
- "bigbench/color",
701
- "bigbench/snarks",
702
- "bigbench/odd_one_out",
703
- "bigbench/epistemic_reasoning",
704
- "bigbench/emojis_emotion_prediction",
705
- "bigbench/metaphor_understanding",
706
- "bigbench/human_organs_senses",
707
  "bigbench/simple_ethical_questions",
 
 
 
 
 
 
 
 
708
  "bigbench/crash_blossom",
709
- "bigbench/authorship_verification",
 
710
  "bigbench/dark_humor_detection",
711
- "bigbench/analogical_similarity",
712
- "bigbench/social_iqa",
713
- "bigbench/figure_of_speech_detection",
714
- "bigbench/sentence_ambiguity",
 
715
  "bigbench/salient_translation_error_detection",
716
- "bigbench/novel_concepts",
717
  "bigbench/anachronisms",
718
- "bigbench/arithmetic",
719
- "bigbench/riddle_sense",
720
- "bigbench/analytic_entailment",
721
- "bigbench/date_understanding",
722
- "bigbench/dyck_languages",
723
- "bigbench/tracking_shuffled_objects",
724
- "bigbench/temporal_sequences",
725
- "bigbench/hyperbaton",
726
- "bigbench/goal_step_wikihow",
727
- "bigbench/international_phonetic_alphabet_nli",
728
  "bigbench/similarities_abstraction",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
729
  "bigbench/checkmate_in_one",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
730
  "cos_e/v1.0",
731
  "cosmos_qa",
732
  "dream",
@@ -760,51 +774,51 @@
760
  "toxic_conversations",
761
  "TuringBench",
762
  "trec",
763
- "vitaminc/tals--vitaminc",
764
  "hope_edi/english",
765
  "rumoureval_2019/RumourEval2019",
766
  "ethos/binary",
767
  "ethos/multilabel",
 
768
  "tweet_eval/sentiment",
769
- "tweet_eval/emotion",
770
- "tweet_eval/hate",
771
  "tweet_eval/irony",
 
 
772
  "tweet_eval/emoji",
773
- "tweet_eval/offensive",
774
  "tweet_eval/stance_abortion",
775
  "tweet_eval/stance_atheism",
776
  "tweet_eval/stance_climate",
777
  "tweet_eval/stance_feminist",
778
  "tweet_eval/stance_hillary",
779
  "discovery/discovery",
780
- "pragmeval/squinky-informativeness",
781
- "pragmeval/squinky-implicature",
782
- "pragmeval/emobank-arousal",
783
  "pragmeval/squinky-formality",
784
- "pragmeval/emobank-dominance",
 
 
785
  "pragmeval/switchboard",
 
786
  "pragmeval/mrda",
787
  "pragmeval/emobank-valence",
788
- "pragmeval/verifiability",
789
  "pragmeval/persuasiveness-strength",
790
- "pragmeval/sarcasm",
791
- "pragmeval/stac",
792
  "pragmeval/persuasiveness-relevance",
793
  "pragmeval/pdtb",
794
- "pragmeval/persuasiveness-premisetype",
795
- "pragmeval/emergent",
796
  "pragmeval/gum",
797
- "pragmeval/persuasiveness-claimtype",
798
- "pragmeval/persuasiveness-eloquence",
799
  "pragmeval/persuasiveness-specificity",
 
 
 
 
 
 
 
800
  "silicone/iemocap",
 
 
801
  "silicone/oasis",
802
  "silicone/maptask",
803
- "silicone/meld_e",
804
- "silicone/meld_s",
805
  "silicone/dyda_da",
806
- "silicone/sem",
807
- "silicone/dyda_e",
808
  "lex_glue/eurlex",
809
  "lex_glue/scotus",
810
  "lex_glue/ledgar",
@@ -834,27 +848,27 @@
834
  "go_emotions/simplified",
835
  "scicite",
836
  "liar",
837
- "lexical_relation_classification/EVALution",
838
- "lexical_relation_classification/BLESS",
839
  "lexical_relation_classification/CogALexV",
 
840
  "lexical_relation_classification/K&H+N",
 
841
  "lexical_relation_classification/ROOT09",
842
- "linguisticprobing/odd_man_out",
843
- "linguisticprobing/tree_depth",
844
- "linguisticprobing/coordination_inversion",
845
- "linguisticprobing/sentence_length",
846
  "linguisticprobing/obj_number",
847
- "linguisticprobing/subj_number",
848
  "linguisticprobing/bigram_shift",
 
 
 
 
849
  "linguisticprobing/top_constituents",
 
850
  "linguisticprobing/past_present",
851
- "crowdflower/political-media-message",
852
- "crowdflower/text_emotion",
853
  "crowdflower/sentiment_nuclear_power",
854
  "crowdflower/tweet_global_warming",
 
 
855
  "crowdflower/corporate-messaging",
856
- "crowdflower/airline-sentiment",
857
  "crowdflower/political-media-audience",
 
858
  "crowdflower/political-media-bias",
859
  "crowdflower/economic-news",
860
  "ethics/commonsense",
@@ -865,11 +879,6 @@
865
  "google_wellformed_query",
866
  "tweets_hate_speech_detection",
867
  "has_part",
868
- "wnut_17/wnut_17",
869
- "ncbi_disease/ncbi_disease",
870
- "acronym_identification",
871
- "jnlpba/jnlpba",
872
- "ontonotes_english/SpeedOfMagic--ontonotes_english",
873
  "blog_authorship_corpus/gender",
874
  "blog_authorship_corpus/age",
875
  "blog_authorship_corpus/job",
@@ -883,13 +892,13 @@
883
  "phrase_similarity",
884
  "scientific-exaggeration-detection",
885
  "quarel",
886
- "fever-evidence-related/mwong--fever-related",
887
  "numer_sense",
888
  "dynasent/dynabench.dynasent.r1.all/r1",
889
  "dynasent/dynabench.dynasent.r2.all/r2",
890
  "Sarcasm_News_Headline",
891
  "sem_eval_2010_task_8",
892
- "auditor_review/demo-org--auditor_review",
893
  "medmcqa",
894
  "Dynasent_Disagreement",
895
  "Politeness_Disagreement",
@@ -918,12 +927,10 @@
918
  "synthetic-instruct-gptj-pairwise",
919
  "scruples",
920
  "wouldyourather",
921
- "attempto-nli",
922
  "defeasible-nli/atomic",
923
  "defeasible-nli/snli",
924
  "help-nli",
925
  "nli-veridicality-transitivity",
926
- "natural-language-satisfiability",
927
  "lonli",
928
  "dadc-limit-nli",
929
  "FLUTE",
@@ -969,10 +976,6 @@
969
  "oasst2_dense_flat/toxicity",
970
  "oasst2_dense_flat/helpfulness",
971
  "mindgames",
972
- "universal_dependencies/en_gum/deprel",
973
- "universal_dependencies/en_partut/deprel",
974
- "universal_dependencies/en_ewt/deprel",
975
- "universal_dependencies/en_lines/deprel",
976
  "ambient",
977
  "path-naturalness-prediction",
978
  "civil_comments/toxicity",
@@ -989,21 +992,12 @@
989
  "Touche23-ValueEval",
990
  "starcon",
991
  "banking77",
992
- "lsat_qa/all",
993
  "ConTRoL-nli",
994
  "tracie",
995
  "sherliic",
996
  "sen-making/1",
997
  "sen-making/2",
998
  "winowhy",
999
- "mbib-base/cognitive-bias",
1000
- "mbib-base/fake-news",
1001
- "mbib-base/gender-bias",
1002
- "mbib-base/hate-speech",
1003
- "mbib-base/linguistic-bias",
1004
- "mbib-base/political-bias",
1005
- "mbib-base/racial-bias",
1006
- "mbib-base/text-level-bias",
1007
  "robustLR",
1008
  "v1/gen_train234_test2to10",
1009
  "logical-fallacy",
@@ -1012,13 +1006,9 @@
1012
  "subjectivity",
1013
  "MOH",
1014
  "VUAC",
1015
- "TroFi",
1016
  "sharc_modified/mod",
1017
  "conceptrules_v2",
1018
  "disrpt/eng.dep.scidtb.rels",
1019
- "conll2000",
1020
- "few-nerd/supervised",
1021
- "finer-139",
1022
  "zero-shot-label-nli",
1023
  "com2sense",
1024
  "scone",
@@ -1037,7 +1027,8 @@
1037
  "esci",
1038
  "chatbot_arena_conversations",
1039
  "dnd_style_intents",
1040
- "FLD.v2",
 
1041
  "SDOH-NLI",
1042
  "scifact_entailment",
1043
  "feasibilityQA",
@@ -1051,23 +1042,68 @@
1051
  "stepgame",
1052
  "nlgraph",
1053
  "oasst2_pairwise_rlhf_reward",
1054
- "hh-rlhf/helpful-rejection-sampled",
1055
  "hh-rlhf/helpful-base",
1056
  "hh-rlhf/helpful-online",
 
1057
  "hh-rlhf/harmless-base",
1058
  "ruletaker",
1059
  "PARARULE-Plus",
1060
  "proofwriter",
1061
  "logical-entailment",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1062
  "babi_nli",
1063
  "gen_debiased_nli",
1064
  "imppres/presupposition",
1065
  "/prag",
1066
- "blimp-2",
1067
- "mmlu-4"
1068
  ],
1069
  "torch_dtype": "float32",
1070
- "transformers_version": "4.34.1",
1071
  "type_vocab_size": 0,
1072
  "vocab_size": 128100
1073
  }
 
27
  2,
28
  2,
29
  3,
 
30
  2,
31
+ 6,
32
  2,
33
  2,
34
  2,
 
68
  3,
69
  3,
70
  3,
 
71
  2,
72
  2,
73
  2,
74
  2,
 
 
 
75
  1,
76
  1,
77
  1,
 
213
  4,
214
  2,
215
  8,
216
+ 2,
217
  3,
 
218
  2,
219
  2,
220
+ 4,
221
  20,
 
222
  3,
223
  3,
224
  3,
 
229
  2,
230
  2,
231
  2,
 
232
  41,
233
+ 3,
234
  51,
235
  2,
 
236
  2,
237
  2,
 
238
  2,
239
  16,
 
 
240
  17,
241
+ 18,
242
+ 2,
243
  2,
244
  2,
245
+ 3,
246
+ 8,
247
+ 3,
248
+ 7,
249
+ 7,
250
  11,
251
+ 3,
252
+ 3,
253
  42,
254
  12,
 
 
255
  4,
 
 
256
  100,
257
  13,
258
  100,
 
282
  28,
283
  3,
284
  6,
 
 
285
  5,
286
+ 7,
287
  4,
288
+ 6,
289
  3,
290
  2,
291
+ 2,
292
  2,
293
  6,
294
  2,
295
+ 7,
296
+ 20,
297
  2,
298
  2,
299
+ 4,
300
  2,
301
  9,
302
  13,
303
  4,
304
  2,
 
305
  3,
306
  2,
 
307
  3,
308
  2,
309
  2,
 
313
  1,
314
  2,
315
  1,
 
 
 
 
 
316
  2,
317
  49,
318
  40,
 
361
  1,
362
  2,
363
  1,
 
 
364
  2,
365
  2,
366
  2,
 
410
  1,
411
  1,
412
  2,
 
 
 
 
413
  2,
414
  1,
415
  1,
 
426
  2,
427
  2,
428
  77,
 
429
  3,
430
  2,
431
  2,
432
  1,
433
  1,
434
  2,
 
 
 
 
 
 
 
 
435
  3,
436
  18,
437
  13,
 
440
  2,
441
  2,
442
  2,
 
443
  4,
444
  2,
445
  24,
 
 
 
446
  3,
447
  2,
448
  2,
 
462
  1,
463
  17,
464
  3,
465
+ 3,
466
  2,
467
  3,
468
  2,
 
484
  2,
485
  3,
486
  2,
487
+ 3,
488
+ 4,
489
+ 3,
490
+ 3,
491
+ 2,
492
+ 1,
493
+ 1,
494
+ 2,
495
+ 1,
496
+ 1,
497
+ 6,
498
  2,
499
  3,
500
  3,
501
+ 1,
502
+ 1,
503
+ 2,
504
+ 2,
505
+ 10,
506
+ 2,
507
+ 2,
508
+ 2,
509
+ 5,
510
+ 5,
511
+ 5,
512
+ 5,
513
+ 5,
514
+ 5,
515
+ 5,
516
+ 5,
517
+ 5,
518
+ 5,
519
+ 4,
520
+ 1,
521
+ 7,
522
+ 6,
523
+ 6,
524
+ 6,
525
+ 6,
526
+ 6,
527
+ 6,
528
  3,
529
+ 2,
530
  1,
531
+ 2,
532
+ 2,
533
+ 2,
534
+ 3,
535
+ 3,
536
+ 3,
537
  1
538
  ],
539
  "hidden_act": "gelu",
 
552
  "neutral": 1
553
  },
554
  "layer_norm_eps": 1e-07,
555
+ "max_position_embeddings": 1680,
556
  "max_relative_positions": -1,
557
  "model_type": "deberta-v2",
558
  "norm_rel_ebd": "layer_norm",
 
593
  "scitail/snli_format",
594
  "hans",
595
  "WANLI",
 
 
596
  "recast/recast_ner",
597
+ "recast/recast_kg_relations",
 
 
598
  "recast/recast_puns",
599
+ "recast/recast_verbcorner",
600
  "recast/recast_sentiment",
601
+ "recast/recast_verbnet",
602
+ "recast/recast_factuality",
603
+ "recast/recast_megaveridicality",
604
  "probability_words_nli/reasoning_2hop",
605
  "probability_words_nli/reasoning_1hop",
606
  "probability_words_nli/usnli",
607
+ "nan-nli",
608
  "nli_fever",
609
  "breaking_nli",
610
  "conj_nli",
 
629
  "add_one_rte",
630
  "imppres/implicature_quantifiers/log",
631
  "imppres/implicature_numerals_2_3/log",
 
632
  "imppres/implicature_gradable_adjective/log",
633
  "imppres/implicature_connectives/log",
634
+ "imppres/implicature_modals/log",
635
  "imppres/implicature_numerals_10_100/log",
636
  "imppres/implicature_gradable_verb/log",
 
637
  "hlgd",
638
  "paws/labeled_final",
639
  "paws/labeled_swap",
640
  "medical_questions_pairs",
 
 
 
641
  "model-written-evals",
642
  "truthful_qa/multiple_choice",
643
  "fig-qa",
 
 
 
 
 
 
 
 
644
  "bigbench/bbq_lite_json",
645
+ "bigbench/english_proverbs",
646
+ "bigbench/figure_of_speech_detection",
647
+ "bigbench/emoji_movie",
648
+ "bigbench/date_understanding",
649
+ "bigbench/metaphor_understanding",
 
 
 
650
  "bigbench/logical_fallacy_detection",
651
+ "bigbench/analogical_similarity",
 
 
 
652
  "bigbench/mnist_ascii",
 
 
 
653
  "bigbench/elementary_math_qa",
654
+ "bigbench/snarks",
655
+ "bigbench/social_support",
656
+ "bigbench/logical_deduction",
657
+ "bigbench/emojis_emotion_prediction",
 
 
 
 
 
 
 
 
 
 
658
  "bigbench/sports_understanding",
659
+ "bigbench/cifar10_classification",
660
+ "bigbench/tracking_shuffled_objects",
661
+ "bigbench/physics",
662
+ "bigbench/mathematical_induction",
663
+ "bigbench/movie_dialog_same_or_different",
664
+ "bigbench/goal_step_wikihow",
 
 
 
 
 
 
 
665
  "bigbench/strategyqa",
666
+ "bigbench/identify_math_theorems",
 
 
 
667
  "bigbench/gre_reading_comprehension",
668
+ "bigbench/novel_concepts",
669
+ "bigbench/conceptual_combinations",
670
+ "bigbench/hyperbaton",
 
 
671
  "bigbench/strange_stories",
672
+ "bigbench/contextual_parametric_knowledge_conflicts",
673
+ "bigbench/implicatures",
674
+ "bigbench/penguins_in_a_table",
675
+ "bigbench/logical_sequence",
 
 
 
 
 
 
676
  "bigbench/simple_ethical_questions",
677
+ "bigbench/dyck_languages",
678
+ "bigbench/geometric_shapes",
679
+ "bigbench/irony_identification",
680
+ "bigbench/intent_recognition",
681
+ "bigbench/logical_args",
682
+ "bigbench/known_unknowns",
683
+ "bigbench/formal_fallacies_syllogisms_negation",
684
+ "bigbench/suicide_risk",
685
  "bigbench/crash_blossom",
686
+ "bigbench/logic_grid_puzzle",
687
+ "bigbench/analytic_entailment",
688
  "bigbench/dark_humor_detection",
689
+ "bigbench/timedial",
690
+ "bigbench/presuppositions_as_nli",
691
+ "bigbench/arithmetic",
692
+ "bigbench/implicit_relations",
693
+ "bigbench/understanding_fables",
694
  "bigbench/salient_translation_error_detection",
 
695
  "bigbench/anachronisms",
696
+ "bigbench/moral_permissibility",
697
+ "bigbench/abstract_narrative_understanding",
698
+ "bigbench/misconceptions",
699
+ "bigbench/nonsense_words_grammar",
700
+ "bigbench/code_line_description",
701
+ "bigbench/sentence_ambiguity",
702
+ "bigbench/disambiguation_qa",
703
+ "bigbench/crass_ai",
 
 
704
  "bigbench/similarities_abstraction",
705
+ "bigbench/authorship_verification",
706
+ "bigbench/phrase_relatedness",
707
+ "bigbench/color",
708
+ "bigbench/hhh_alignment",
709
+ "bigbench/metaphor_boolean",
710
+ "bigbench/fantasy_reasoning",
711
+ "bigbench/ruin_names",
712
+ "bigbench/cause_and_effect",
713
+ "bigbench/temporal_sequences",
714
+ "bigbench/navigate",
715
+ "bigbench/symbol_interpretation",
716
+ "bigbench/key_value_maps",
717
+ "bigbench/entailed_polarity",
718
+ "bigbench/riddle_sense",
719
+ "bigbench/discourse_marker_prediction",
720
+ "bigbench/reasoning_about_colored_objects",
721
+ "bigbench/empirical_judgments",
722
+ "bigbench/fact_checker",
723
+ "bigbench/movie_recommendation",
724
  "bigbench/checkmate_in_one",
725
+ "bigbench/epistemic_reasoning",
726
+ "bigbench/vitaminc_fact_verification",
727
+ "bigbench/general_knowledge",
728
+ "bigbench/identify_odd_metaphor",
729
+ "bigbench/physical_intuition",
730
+ "bigbench/winowhy",
731
+ "bigbench/cs_algorithms",
732
+ "bigbench/undo_permutation",
733
+ "bigbench/evaluating_information_essentiality",
734
+ "bigbench/unit_interpretation",
735
+ "bigbench/question_selection",
736
+ "bigbench/international_phonetic_alphabet_nli",
737
+ "bigbench/play_dialog_same_or_different",
738
+ "bigbench/real_or_fake_text",
739
+ "bigbench/human_organs_senses",
740
+ "bigbench/hindu_knowledge",
741
+ "bigbench/social_iqa",
742
+ "bigbench/odd_one_out",
743
+ "bigbench/causal_judgment",
744
  "cos_e/v1.0",
745
  "cosmos_qa",
746
  "dream",
 
774
  "toxic_conversations",
775
  "TuringBench",
776
  "trec",
777
+ "vitaminc",
778
  "hope_edi/english",
779
  "rumoureval_2019/RumourEval2019",
780
  "ethos/binary",
781
  "ethos/multilabel",
782
+ "tweet_eval/offensive",
783
  "tweet_eval/sentiment",
 
 
784
  "tweet_eval/irony",
785
+ "tweet_eval/hate",
786
+ "tweet_eval/emotion",
787
  "tweet_eval/emoji",
 
788
  "tweet_eval/stance_abortion",
789
  "tweet_eval/stance_atheism",
790
  "tweet_eval/stance_climate",
791
  "tweet_eval/stance_feminist",
792
  "tweet_eval/stance_hillary",
793
  "discovery/discovery",
 
 
 
794
  "pragmeval/squinky-formality",
795
+ "pragmeval/emobank-arousal",
796
+ "pragmeval/squinky-implicature",
797
+ "pragmeval/squinky-informativeness",
798
  "pragmeval/switchboard",
799
+ "pragmeval/verifiability",
800
  "pragmeval/mrda",
801
  "pragmeval/emobank-valence",
802
+ "pragmeval/emobank-dominance",
803
  "pragmeval/persuasiveness-strength",
 
 
804
  "pragmeval/persuasiveness-relevance",
805
  "pragmeval/pdtb",
 
 
806
  "pragmeval/gum",
807
+ "pragmeval/stac",
 
808
  "pragmeval/persuasiveness-specificity",
809
+ "pragmeval/sarcasm",
810
+ "pragmeval/persuasiveness-eloquence",
811
+ "pragmeval/emergent",
812
+ "pragmeval/persuasiveness-premisetype",
813
+ "pragmeval/persuasiveness-claimtype",
814
+ "silicone/meld_e",
815
+ "silicone/dyda_e",
816
  "silicone/iemocap",
817
+ "silicone/sem",
818
+ "silicone/meld_s",
819
  "silicone/oasis",
820
  "silicone/maptask",
 
 
821
  "silicone/dyda_da",
 
 
822
  "lex_glue/eurlex",
823
  "lex_glue/scotus",
824
  "lex_glue/ledgar",
 
848
  "go_emotions/simplified",
849
  "scicite",
850
  "liar",
 
 
851
  "lexical_relation_classification/CogALexV",
852
+ "lexical_relation_classification/EVALution",
853
  "lexical_relation_classification/K&H+N",
854
+ "lexical_relation_classification/BLESS",
855
  "lexical_relation_classification/ROOT09",
 
 
 
 
856
  "linguisticprobing/obj_number",
 
857
  "linguisticprobing/bigram_shift",
858
+ "linguisticprobing/subj_number",
859
+ "linguisticprobing/sentence_length",
860
+ "linguisticprobing/odd_man_out",
861
+ "linguisticprobing/tree_depth",
862
  "linguisticprobing/top_constituents",
863
+ "linguisticprobing/coordination_inversion",
864
  "linguisticprobing/past_present",
 
 
865
  "crowdflower/sentiment_nuclear_power",
866
  "crowdflower/tweet_global_warming",
867
+ "crowdflower/political-media-message",
868
+ "crowdflower/text_emotion",
869
  "crowdflower/corporate-messaging",
 
870
  "crowdflower/political-media-audience",
871
+ "crowdflower/airline-sentiment",
872
  "crowdflower/political-media-bias",
873
  "crowdflower/economic-news",
874
  "ethics/commonsense",
 
879
  "google_wellformed_query",
880
  "tweets_hate_speech_detection",
881
  "has_part",
 
 
 
 
 
882
  "blog_authorship_corpus/gender",
883
  "blog_authorship_corpus/age",
884
  "blog_authorship_corpus/job",
 
892
  "phrase_similarity",
893
  "scientific-exaggeration-detection",
894
  "quarel",
895
+ "fever-evidence-related",
896
  "numer_sense",
897
  "dynasent/dynabench.dynasent.r1.all/r1",
898
  "dynasent/dynabench.dynasent.r2.all/r2",
899
  "Sarcasm_News_Headline",
900
  "sem_eval_2010_task_8",
901
+ "auditor_review",
902
  "medmcqa",
903
  "Dynasent_Disagreement",
904
  "Politeness_Disagreement",
 
927
  "synthetic-instruct-gptj-pairwise",
928
  "scruples",
929
  "wouldyourather",
 
930
  "defeasible-nli/atomic",
931
  "defeasible-nli/snli",
932
  "help-nli",
933
  "nli-veridicality-transitivity",
 
934
  "lonli",
935
  "dadc-limit-nli",
936
  "FLUTE",
 
976
  "oasst2_dense_flat/toxicity",
977
  "oasst2_dense_flat/helpfulness",
978
  "mindgames",
 
 
 
 
979
  "ambient",
980
  "path-naturalness-prediction",
981
  "civil_comments/toxicity",
 
992
  "Touche23-ValueEval",
993
  "starcon",
994
  "banking77",
 
995
  "ConTRoL-nli",
996
  "tracie",
997
  "sherliic",
998
  "sen-making/1",
999
  "sen-making/2",
1000
  "winowhy",
 
 
 
 
 
 
 
 
1001
  "robustLR",
1002
  "v1/gen_train234_test2to10",
1003
  "logical-fallacy",
 
1006
  "subjectivity",
1007
  "MOH",
1008
  "VUAC",
 
1009
  "sharc_modified/mod",
1010
  "conceptrules_v2",
1011
  "disrpt/eng.dep.scidtb.rels",
 
 
 
1012
  "zero-shot-label-nli",
1013
  "com2sense",
1014
  "scone",
 
1027
  "esci",
1028
  "chatbot_arena_conversations",
1029
  "dnd_style_intents",
1030
+ "FLD.v2/default",
1031
+ "FLD.v2/star",
1032
  "SDOH-NLI",
1033
  "scifact_entailment",
1034
  "feasibilityQA",
 
1042
  "stepgame",
1043
  "nlgraph",
1044
  "oasst2_pairwise_rlhf_reward",
 
1045
  "hh-rlhf/helpful-base",
1046
  "hh-rlhf/helpful-online",
1047
+ "hh-rlhf/helpful-rejection-sampled",
1048
  "hh-rlhf/harmless-base",
1049
  "ruletaker",
1050
  "PARARULE-Plus",
1051
  "proofwriter",
1052
  "logical-entailment",
1053
+ "nope",
1054
+ "LogicNLI",
1055
+ "contract-nli/contractnli_a/seg",
1056
+ "contract-nli/contractnli_b/full",
1057
+ "nli4ct_semeval2024",
1058
+ "lsat-ar",
1059
+ "lsat-rc",
1060
+ "biosift-nli",
1061
+ "brainteasers/WP",
1062
+ "brainteasers/SP",
1063
+ "persuasion",
1064
+ "AmbigNQ-clarifying-question",
1065
+ "SIGA-nli",
1066
+ "FOL-nli",
1067
+ "goal-step-wikihow/order",
1068
+ "PARADISE",
1069
+ "doc-nli",
1070
+ "mctest-nli",
1071
+ "patent-phrase-similarity",
1072
+ "natural-language-satisfiability",
1073
+ "idioms-nli",
1074
+ "lifecycle-entailment",
1075
+ "HelpSteer/helpfulness",
1076
+ "HelpSteer/correctness",
1077
+ "HelpSteer/coherence",
1078
+ "HelpSteer/complexity",
1079
+ "HelpSteer/verbosity",
1080
+ "HelpSteer2/helpfulness",
1081
+ "HelpSteer2/correctness",
1082
+ "HelpSteer2/coherence",
1083
+ "HelpSteer2/complexity",
1084
+ "HelpSteer2/verbosity",
1085
+ "MSciNLI",
1086
+ "UltraFeedback-paired",
1087
+ "AES2-essay-scoring",
1088
+ "english-grading/cohesion",
1089
+ "english-grading/syntax",
1090
+ "english-grading/vocabulary",
1091
+ "english-grading/phraseology",
1092
+ "english-grading/grammar",
1093
+ "english-grading/conventions",
1094
+ "wice",
1095
+ "hover",
1096
+ "tasksource_dpo_pairs",
1097
+ "seahorse_summarization_evaluation",
1098
+ "missing-item-prediction/contrastive",
1099
  "babi_nli",
1100
  "gen_debiased_nli",
1101
  "imppres/presupposition",
1102
  "/prag",
1103
+ "blimp-2"
 
1104
  ],
1105
  "torch_dtype": "float32",
1106
+ "transformers_version": "4.42.3",
1107
  "type_vocab_size": 0,
1108
  "vocab_size": 128100
1109
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9af30c7ad7235a2054300bc2df1d98149ad6008dd1ef06212be8b32b5d1b3458
3
+ size 567601628