sileod commited on
Commit
eced9db
1 Parent(s): 12813ee

Upload DebertaV2ForSequenceClassification

Browse files
Files changed (2) hide show
  1. config.json +135 -131
  2. pytorch_model.bin +1 -1
config.json CHANGED
@@ -218,7 +218,6 @@
218
  4,
219
  2,
220
  8,
221
- 2,
222
  4,
223
  2,
224
  2,
@@ -229,35 +228,36 @@
229
  3,
230
  3,
231
  20,
 
232
  174,
233
  2,
 
234
  2,
235
  2,
236
  2,
237
  2,
238
- 41,
239
- 51,
240
- 3,
241
  2,
 
242
  3,
243
- 18,
244
- 17,
245
  3,
246
  2,
247
- 16,
 
 
248
  2,
249
  2,
250
- 8,
251
  2,
252
  2,
253
- 7,
254
- 4,
255
- 7,
256
  3,
257
  42,
258
  3,
 
259
  12,
260
- 11,
 
261
  100,
262
  13,
263
  100,
@@ -287,29 +287,29 @@
287
  28,
288
  3,
289
  6,
290
- 5,
291
  7,
292
  3,
293
- 6,
294
  4,
295
  2,
296
  20,
297
- 6,
298
  2,
299
  2,
300
  2,
301
  2,
302
  2,
 
303
  7,
304
  2,
 
 
305
  2,
306
  3,
307
  4,
308
- 9,
309
  2,
310
- 4,
311
  3,
312
- 13,
313
  2,
314
  2,
315
  2,
@@ -334,7 +334,6 @@
334
  2,
335
  1,
336
  5,
337
- 3,
338
  2,
339
  3,
340
  2,
@@ -489,6 +488,9 @@
489
  3,
490
  2,
491
  3,
 
 
 
492
  2,
493
  3,
494
  3,
@@ -606,106 +608,106 @@
606
  "model-written-evals",
607
  "truthful_qa/multiple_choice",
608
  "fig-qa",
609
- "bigbench/sports_understanding",
610
- "bigbench/analytic_entailment",
611
- "bigbench/presuppositions_as_nli",
612
- "bigbench/logic_grid_puzzle",
613
- "bigbench/geometric_shapes",
614
- "bigbench/metaphor_understanding",
615
- "bigbench/movie_recommendation",
616
- "bigbench/gre_reading_comprehension",
617
  "bigbench/logical_args",
618
- "bigbench/similarities_abstraction",
619
  "bigbench/nonsense_words_grammar",
620
- "bigbench/misconceptions",
621
- "bigbench/winowhy",
622
- "bigbench/understanding_fables",
623
- "bigbench/logical_sequence",
624
- "bigbench/hyperbaton",
625
- "bigbench/emojis_emotion_prediction",
626
- "bigbench/discourse_marker_prediction",
627
- "bigbench/cause_and_effect",
628
- "bigbench/crass_ai",
629
- "bigbench/real_or_fake_text",
630
- "bigbench/date_understanding",
631
- "bigbench/analogical_similarity",
632
  "bigbench/crash_blossom",
633
- "bigbench/undo_permutation",
634
  "bigbench/english_proverbs",
 
 
 
 
 
 
 
 
 
635
  "bigbench/logical_fallacy_detection",
 
636
  "bigbench/question_selection",
637
- "bigbench/human_organs_senses",
638
- "bigbench/cifar10_classification",
639
- "bigbench/social_iqa",
640
- "bigbench/abstract_narrative_understanding",
641
- "bigbench/emoji_movie",
642
- "bigbench/sentence_ambiguity",
643
- "bigbench/elementary_math_qa",
644
- "bigbench/epistemic_reasoning",
645
- "bigbench/metaphor_boolean",
646
- "bigbench/tracking_shuffled_objects",
647
- "bigbench/physical_intuition",
648
- "bigbench/key_value_maps",
649
- "bigbench/penguins_in_a_table",
650
  "bigbench/formal_fallacies_syllogisms_negation",
 
 
 
651
  "bigbench/riddle_sense",
652
- "bigbench/logical_deduction",
653
- "bigbench/entailed_polarity",
654
- "bigbench/ruin_names",
655
- "bigbench/timedial",
656
- "bigbench/fantasy_reasoning",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
657
  "bigbench/causal_judgment",
658
- "bigbench/social_support",
659
- "bigbench/disambiguation_qa",
660
- "bigbench/hindu_knowledge",
661
  "bigbench/play_dialog_same_or_different",
662
- "bigbench/intent_recognition",
663
- "bigbench/code_line_description",
664
- "bigbench/implicit_relations",
665
- "bigbench/checkmate_in_one",
 
 
 
 
 
 
 
666
  "bigbench/dark_humor_detection",
667
- "bigbench/mathematical_induction",
668
- "bigbench/identify_odd_metaphor",
669
- "bigbench/implicatures",
670
- "bigbench/irony_identification",
671
- "bigbench/phrase_relatedness",
672
  "bigbench/figure_of_speech_detection",
673
- "bigbench/empirical_judgments",
674
- "bigbench/identify_math_theorems",
675
- "bigbench/evaluating_information_essentiality",
676
- "bigbench/hhh_alignment",
677
- "bigbench/reasoning_about_colored_objects",
678
- "bigbench/goal_step_wikihow",
679
- "bigbench/odd_one_out",
680
- "bigbench/strategyqa",
681
  "bigbench/international_phonetic_alphabet_nli",
682
- "bigbench/known_unknowns",
683
- "bigbench/anachronisms",
684
- "bigbench/bbq_lite_json",
685
- "bigbench/mnist_ascii",
686
- "bigbench/novel_concepts",
687
  "bigbench/authorship_verification",
 
 
 
688
  "bigbench/physics",
689
- "bigbench/vitaminc_fact_verification",
690
  "bigbench/general_knowledge",
691
- "bigbench/simple_ethical_questions",
692
- "bigbench/snarks",
693
- "bigbench/symbol_interpretation",
694
- "bigbench/moral_permissibility",
695
- "bigbench/arithmetic",
696
- "bigbench/navigate",
697
- "bigbench/cs_algorithms",
698
- "bigbench/temporal_sequences",
699
  "bigbench/unit_interpretation",
700
- "bigbench/movie_dialog_same_or_different",
701
- "bigbench/fact_checker",
702
  "bigbench/suicide_risk",
703
- "bigbench/conceptual_combinations",
 
704
  "bigbench/strange_stories",
705
- "bigbench/dyck_languages",
 
 
 
706
  "bigbench/contextual_parametric_knowledge_conflicts",
707
- "bigbench/salient_translation_error_detection",
708
- "bigbench/color",
 
709
  "cos_e/v1.0",
710
  "cosmos_qa",
711
  "dream",
@@ -744,7 +746,6 @@
744
  "rumoureval_2019/RumourEval2019",
745
  "ethos/binary",
746
  "ethos/multilabel",
747
- "tweet_eval/hate",
748
  "tweet_eval/emotion",
749
  "tweet_eval/irony",
750
  "tweet_eval/offensive",
@@ -755,35 +756,36 @@
755
  "tweet_eval/stance_feminist",
756
  "tweet_eval/stance_hillary",
757
  "tweet_eval/emoji",
 
758
  "discovery/discovery",
759
- "pragmeval/squinky-formality",
760
  "pragmeval/emobank-valence",
 
761
  "pragmeval/emobank-dominance",
 
 
762
  "pragmeval/squinky-implicature",
763
  "pragmeval/squinky-informativeness",
764
- "pragmeval/switchboard",
765
  "pragmeval/mrda",
766
  "pragmeval/verifiability",
767
- "pragmeval/emobank-arousal",
768
- "pragmeval/emergent",
769
- "pragmeval/stac",
770
- "pragmeval/gum",
771
  "pragmeval/persuasiveness-claimtype",
772
  "pragmeval/persuasiveness-eloquence",
773
- "pragmeval/pdtb",
774
- "pragmeval/persuasiveness-relevance",
775
- "pragmeval/sarcasm",
776
  "pragmeval/persuasiveness-premisetype",
777
- "pragmeval/persuasiveness-strength",
 
778
  "pragmeval/persuasiveness-specificity",
779
- "silicone/dyda_e",
780
- "silicone/dyda_da",
781
- "silicone/meld_e",
782
- "silicone/meld_s",
783
- "silicone/oasis",
784
  "silicone/sem",
 
 
 
785
  "silicone/maptask",
786
- "silicone/iemocap",
 
787
  "lex_glue/eurlex",
788
  "lex_glue/scotus",
789
  "lex_glue/ledgar",
@@ -813,29 +815,29 @@
813
  "go_emotions/simplified",
814
  "scicite",
815
  "liar",
816
- "lexical_relation_classification/CogALexV",
817
  "lexical_relation_classification/EVALution",
818
  "lexical_relation_classification/ROOT09",
819
- "lexical_relation_classification/BLESS",
820
  "lexical_relation_classification/K&H+N",
821
  "linguisticprobing/bigram_shift",
822
  "linguisticprobing/top_constituents",
823
- "linguisticprobing/sentence_length",
824
  "linguisticprobing/subj_number",
825
- "linguisticprobing/obj_number",
826
- "linguisticprobing/past_present",
827
  "linguisticprobing/odd_man_out",
828
  "linguisticprobing/coordination_inversion",
 
 
 
829
  "linguisticprobing/tree_depth",
830
  "crowdflower/tweet_global_warming",
831
- "crowdflower/political-media-audience",
832
- "crowdflower/economic-news",
833
- "crowdflower/sentiment_nuclear_power",
834
  "crowdflower/political-media-message",
835
  "crowdflower/political-media-bias",
836
- "crowdflower/corporate-messaging",
837
  "crowdflower/airline-sentiment",
838
- "crowdflower/text_emotion",
 
 
 
839
  "ethics/commonsense",
840
  "ethics/deontology",
841
  "ethics/justice",
@@ -860,7 +862,6 @@
860
  "ade_corpus_v2/Ade_corpus_v2_classification",
861
  "discosense",
862
  "circa",
863
- "EffectiveFeedbackStudentWriting",
864
  "phrase_similarity",
865
  "scientific-exaggeration-detection",
866
  "quarel",
@@ -900,8 +901,8 @@
900
  "scruples",
901
  "wouldyourather",
902
  "attempto-nli",
903
- "defeasible-nli/atomic",
904
  "defeasible-nli/snli",
 
905
  "help-nli",
906
  "nli-veridicality-transitivity",
907
  "natural-language-satisfiability",
@@ -924,8 +925,8 @@
924
  "redefine-math",
925
  "puzzte",
926
  "implicatures",
927
- "race/high",
928
  "race/middle",
 
929
  "race-c",
930
  "spartqa-yn",
931
  "spartqa-mchoice",
@@ -951,10 +952,10 @@
951
  "oasst1_dense_flat/helpfulness",
952
  "PARARULE-Plus",
953
  "mindgames",
954
- "universal_dependencies/en_ewt/deprel",
955
  "universal_dependencies/en_gum/deprel",
956
- "universal_dependencies/en_lines/deprel",
957
  "universal_dependencies/en_partut/deprel",
 
958
  "ambient",
959
  "path-naturalness-prediction",
960
  "civil_comments/toxicity",
@@ -1015,6 +1016,9 @@
1015
  "twitter-financial-news-sentiment",
1016
  "icl-symbol-tuning-instruct",
1017
  "SpaceNLI",
 
 
 
1018
  "babi_nli",
1019
  "gen_debiased_nli",
1020
  "imppres/presupposition",
 
218
  4,
219
  2,
220
  8,
 
221
  4,
222
  2,
223
  2,
 
228
  3,
229
  3,
230
  20,
231
+ 2,
232
  174,
233
  2,
234
+ 41,
235
  2,
236
  2,
237
  2,
238
  2,
 
 
 
239
  2,
240
+ 51,
241
  3,
242
+ 16,
 
243
  3,
244
  2,
245
+ 8,
246
+ 17,
247
+ 18,
248
  2,
249
  2,
 
250
  2,
251
  2,
252
+ 3,
253
+ 11,
 
254
  3,
255
  42,
256
  3,
257
+ 7,
258
  12,
259
+ 7,
260
+ 4,
261
  100,
262
  13,
263
  100,
 
287
  28,
288
  3,
289
  6,
290
+ 6,
291
  7,
292
  3,
293
+ 5,
294
  4,
295
  2,
296
  20,
 
297
  2,
298
  2,
299
  2,
300
  2,
301
  2,
302
+ 6,
303
  7,
304
  2,
305
+ 13,
306
+ 9,
307
  2,
308
  3,
309
  4,
 
310
  2,
 
311
  3,
312
+ 4,
313
  2,
314
  2,
315
  2,
 
334
  2,
335
  1,
336
  5,
 
337
  2,
338
  3,
339
  2,
 
488
  3,
489
  2,
490
  3,
491
+ 3,
492
+ 2,
493
+ 2,
494
  2,
495
  3,
496
  3,
 
608
  "model-written-evals",
609
  "truthful_qa/multiple_choice",
610
  "fig-qa",
611
+ "bigbench/navigate",
 
 
 
 
 
 
 
612
  "bigbench/logical_args",
613
+ "bigbench/implicatures",
614
  "bigbench/nonsense_words_grammar",
615
+ "bigbench/tracking_shuffled_objects",
616
+ "bigbench/simple_ethical_questions",
617
+ "bigbench/metaphor_understanding",
618
+ "bigbench/novel_concepts",
619
+ "bigbench/emoji_movie",
620
+ "bigbench/social_iqa",
621
+ "bigbench/social_support",
 
 
 
 
 
622
  "bigbench/crash_blossom",
623
+ "bigbench/empirical_judgments",
624
  "bigbench/english_proverbs",
625
+ "bigbench/mnist_ascii",
626
+ "bigbench/emojis_emotion_prediction",
627
+ "bigbench/hhh_alignment",
628
+ "bigbench/hyperbaton",
629
+ "bigbench/intent_recognition",
630
+ "bigbench/odd_one_out",
631
+ "bigbench/analytic_entailment",
632
+ "bigbench/mathematical_induction",
633
+ "bigbench/cifar10_classification",
634
  "bigbench/logical_fallacy_detection",
635
+ "bigbench/logical_deduction",
636
  "bigbench/question_selection",
 
 
 
 
 
 
 
 
 
 
 
 
 
637
  "bigbench/formal_fallacies_syllogisms_negation",
638
+ "bigbench/identify_odd_metaphor",
639
+ "bigbench/logic_grid_puzzle",
640
+ "bigbench/reasoning_about_colored_objects",
641
  "bigbench/riddle_sense",
642
+ "bigbench/bbq_lite_json",
643
+ "bigbench/similarities_abstraction",
644
+ "bigbench/logical_sequence",
645
+ "bigbench/undo_permutation",
646
+ "bigbench/misconceptions",
647
+ "bigbench/movie_recommendation",
648
+ "bigbench/anachronisms",
649
+ "bigbench/symbol_interpretation",
650
+ "bigbench/snarks",
651
+ "bigbench/key_value_maps",
652
+ "bigbench/goal_step_wikihow",
653
+ "bigbench/vitaminc_fact_verification",
654
+ "bigbench/known_unknowns",
655
+ "bigbench/cs_algorithms",
656
+ "bigbench/arithmetic",
657
+ "bigbench/epistemic_reasoning",
658
+ "bigbench/color",
659
+ "bigbench/phrase_relatedness",
660
+ "bigbench/gre_reading_comprehension",
661
+ "bigbench/date_understanding",
662
+ "bigbench/metaphor_boolean",
663
+ "bigbench/strategyqa",
664
+ "bigbench/understanding_fables",
665
  "bigbench/causal_judgment",
 
 
 
666
  "bigbench/play_dialog_same_or_different",
667
+ "bigbench/conceptual_combinations",
668
+ "bigbench/sports_understanding",
669
+ "bigbench/dyck_languages",
670
+ "bigbench/salient_translation_error_detection",
671
+ "bigbench/sentence_ambiguity",
672
+ "bigbench/entailed_polarity",
673
+ "bigbench/timedial",
674
+ "bigbench/ruin_names",
675
+ "bigbench/physical_intuition",
676
+ "bigbench/winowhy",
677
+ "bigbench/evaluating_information_essentiality",
678
  "bigbench/dark_humor_detection",
679
+ "bigbench/moral_permissibility",
680
+ "bigbench/code_line_description",
681
+ "bigbench/temporal_sequences",
 
 
682
  "bigbench/figure_of_speech_detection",
683
+ "bigbench/fantasy_reasoning",
684
+ "bigbench/fact_checker",
685
+ "bigbench/geometric_shapes",
 
 
 
 
 
686
  "bigbench/international_phonetic_alphabet_nli",
 
 
 
 
 
687
  "bigbench/authorship_verification",
688
+ "bigbench/human_organs_senses",
689
+ "bigbench/irony_identification",
690
+ "bigbench/presuppositions_as_nli",
691
  "bigbench/physics",
 
692
  "bigbench/general_knowledge",
693
+ "bigbench/identify_math_theorems",
694
+ "bigbench/penguins_in_a_table",
695
+ "bigbench/hindu_knowledge",
696
+ "bigbench/checkmate_in_one",
 
 
 
 
697
  "bigbench/unit_interpretation",
698
+ "bigbench/real_or_fake_text",
 
699
  "bigbench/suicide_risk",
700
+ "bigbench/implicit_relations",
701
+ "bigbench/abstract_narrative_understanding",
702
  "bigbench/strange_stories",
703
+ "bigbench/cause_and_effect",
704
+ "bigbench/disambiguation_qa",
705
+ "bigbench/movie_dialog_same_or_different",
706
+ "bigbench/elementary_math_qa",
707
  "bigbench/contextual_parametric_knowledge_conflicts",
708
+ "bigbench/crass_ai",
709
+ "bigbench/analogical_similarity",
710
+ "bigbench/discourse_marker_prediction",
711
  "cos_e/v1.0",
712
  "cosmos_qa",
713
  "dream",
 
746
  "rumoureval_2019/RumourEval2019",
747
  "ethos/binary",
748
  "ethos/multilabel",
 
749
  "tweet_eval/emotion",
750
  "tweet_eval/irony",
751
  "tweet_eval/offensive",
 
756
  "tweet_eval/stance_feminist",
757
  "tweet_eval/stance_hillary",
758
  "tweet_eval/emoji",
759
+ "tweet_eval/hate",
760
  "discovery/discovery",
 
761
  "pragmeval/emobank-valence",
762
+ "pragmeval/switchboard",
763
  "pragmeval/emobank-dominance",
764
+ "pragmeval/emobank-arousal",
765
+ "pragmeval/squinky-formality",
766
  "pragmeval/squinky-implicature",
767
  "pragmeval/squinky-informativeness",
 
768
  "pragmeval/mrda",
769
  "pragmeval/verifiability",
770
+ "pragmeval/pdtb",
 
 
 
771
  "pragmeval/persuasiveness-claimtype",
772
  "pragmeval/persuasiveness-eloquence",
 
 
 
773
  "pragmeval/persuasiveness-premisetype",
774
+ "pragmeval/gum",
775
+ "pragmeval/stac",
776
  "pragmeval/persuasiveness-specificity",
777
+ "pragmeval/persuasiveness-strength",
778
+ "pragmeval/sarcasm",
779
+ "pragmeval/persuasiveness-relevance",
780
+ "pragmeval/emergent",
781
+ "silicone/iemocap",
782
  "silicone/sem",
783
+ "silicone/oasis",
784
+ "silicone/meld_s",
785
+ "silicone/meld_e",
786
  "silicone/maptask",
787
+ "silicone/dyda_e",
788
+ "silicone/dyda_da",
789
  "lex_glue/eurlex",
790
  "lex_glue/scotus",
791
  "lex_glue/ledgar",
 
815
  "go_emotions/simplified",
816
  "scicite",
817
  "liar",
818
+ "lexical_relation_classification/BLESS",
819
  "lexical_relation_classification/EVALution",
820
  "lexical_relation_classification/ROOT09",
821
+ "lexical_relation_classification/CogALexV",
822
  "lexical_relation_classification/K&H+N",
823
  "linguisticprobing/bigram_shift",
824
  "linguisticprobing/top_constituents",
 
825
  "linguisticprobing/subj_number",
 
 
826
  "linguisticprobing/odd_man_out",
827
  "linguisticprobing/coordination_inversion",
828
+ "linguisticprobing/obj_number",
829
+ "linguisticprobing/past_present",
830
+ "linguisticprobing/sentence_length",
831
  "linguisticprobing/tree_depth",
832
  "crowdflower/tweet_global_warming",
833
+ "crowdflower/text_emotion",
 
 
834
  "crowdflower/political-media-message",
835
  "crowdflower/political-media-bias",
 
836
  "crowdflower/airline-sentiment",
837
+ "crowdflower/sentiment_nuclear_power",
838
+ "crowdflower/political-media-audience",
839
+ "crowdflower/economic-news",
840
+ "crowdflower/corporate-messaging",
841
  "ethics/commonsense",
842
  "ethics/deontology",
843
  "ethics/justice",
 
862
  "ade_corpus_v2/Ade_corpus_v2_classification",
863
  "discosense",
864
  "circa",
 
865
  "phrase_similarity",
866
  "scientific-exaggeration-detection",
867
  "quarel",
 
901
  "scruples",
902
  "wouldyourather",
903
  "attempto-nli",
 
904
  "defeasible-nli/snli",
905
+ "defeasible-nli/atomic",
906
  "help-nli",
907
  "nli-veridicality-transitivity",
908
  "natural-language-satisfiability",
 
925
  "redefine-math",
926
  "puzzte",
927
  "implicatures",
 
928
  "race/middle",
929
+ "race/high",
930
  "race-c",
931
  "spartqa-yn",
932
  "spartqa-mchoice",
 
952
  "oasst1_dense_flat/helpfulness",
953
  "PARARULE-Plus",
954
  "mindgames",
 
955
  "universal_dependencies/en_gum/deprel",
956
+ "universal_dependencies/en_ewt/deprel",
957
  "universal_dependencies/en_partut/deprel",
958
+ "universal_dependencies/en_lines/deprel",
959
  "ambient",
960
  "path-naturalness-prediction",
961
  "civil_comments/toxicity",
 
1016
  "twitter-financial-news-sentiment",
1017
  "icl-symbol-tuning-instruct",
1018
  "SpaceNLI",
1019
+ "propsegment/nli",
1020
+ "HatemojiBuild",
1021
+ "regset",
1022
  "babi_nli",
1023
  "gen_debiased_nli",
1024
  "imppres/presupposition",
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a8ff4deb3e99417c600710373a7e73f249ffedade58091d7cae55b372c61743
3
  size 737771833
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab88a8f05db76ac64228169372c5ee6b8dde4f2ec01359411d03b5fd2bc386ba
3
  size 737771833