sileod commited on
Commit
90bdb28
1 Parent(s): f425e40

Upload DebertaV2ForSequenceClassification

Browse files
Files changed (2) hide show
  1. config.json +140 -132
  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,
@@ -487,7 +487,11 @@
487
  1,
488
  2,
489
  3,
 
490
  3,
 
 
 
491
  2,
492
  3,
493
  3,
@@ -605,106 +609,106 @@
605
  "model-written-evals",
606
  "truthful_qa/multiple_choice",
607
  "fig-qa",
608
- "bigbench/logical_sequence",
609
- "bigbench/snarks",
610
- "bigbench/general_knowledge",
611
- "bigbench/moral_permissibility",
612
- "bigbench/figure_of_speech_detection",
613
- "bigbench/abstract_narrative_understanding",
614
- "bigbench/anachronisms",
615
- "bigbench/vitaminc_fact_verification",
616
- "bigbench/authorship_verification",
617
  "bigbench/penguins_in_a_table",
618
- "bigbench/play_dialog_same_or_different",
619
- "bigbench/physical_intuition",
620
- "bigbench/empirical_judgments",
621
- "bigbench/checkmate_in_one",
622
- "bigbench/metaphor_understanding",
623
- "bigbench/cs_algorithms",
624
- "bigbench/dyck_languages",
625
  "bigbench/dark_humor_detection",
 
 
 
 
 
626
  "bigbench/fantasy_reasoning",
 
 
 
627
  "bigbench/odd_one_out",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
628
  "bigbench/epistemic_reasoning",
629
- "bigbench/identify_odd_metaphor",
630
- "bigbench/discourse_marker_prediction",
631
  "bigbench/question_selection",
 
 
 
 
 
 
 
 
632
  "bigbench/geometric_shapes",
633
- "bigbench/date_understanding",
634
- "bigbench/disambiguation_qa",
635
- "bigbench/strategyqa",
636
- "bigbench/color",
 
 
 
637
  "bigbench/elementary_math_qa",
638
- "bigbench/mathematical_induction",
639
- "bigbench/strange_stories",
640
- "bigbench/logical_args",
641
- "bigbench/cifar10_classification",
642
- "bigbench/evaluating_information_essentiality",
643
  "bigbench/novel_concepts",
644
- "bigbench/hyperbaton",
645
- "bigbench/fact_checker",
646
- "bigbench/sentence_ambiguity",
647
- "bigbench/social_iqa",
648
- "bigbench/identify_math_theorems",
649
- "bigbench/cause_and_effect",
 
 
 
 
650
  "bigbench/misconceptions",
651
- "bigbench/causal_judgment",
652
- "bigbench/international_phonetic_alphabet_nli",
653
- "bigbench/implicit_relations",
654
  "bigbench/salient_translation_error_detection",
 
 
 
655
  "bigbench/logical_deduction",
656
- "bigbench/known_unknowns",
657
- "bigbench/arithmetic",
658
- "bigbench/sports_understanding",
659
- "bigbench/navigate",
660
- "bigbench/irony_identification",
661
  "bigbench/hindu_knowledge",
662
- "bigbench/mnist_ascii",
663
- "bigbench/social_support",
664
- "bigbench/presuppositions_as_nli",
665
- "bigbench/tracking_shuffled_objects",
666
- "bigbench/winowhy",
667
- "bigbench/formal_fallacies_syllogisms_negation",
668
- "bigbench/emoji_movie",
669
- "bigbench/code_line_description",
670
- "bigbench/logical_fallacy_detection",
671
- "bigbench/intent_recognition",
672
- "bigbench/bbq_lite_json",
673
- "bigbench/metaphor_boolean",
674
- "bigbench/analytic_entailment",
675
  "bigbench/unit_interpretation",
 
 
 
676
  "bigbench/analogical_similarity",
677
- "bigbench/symbol_interpretation",
678
- "bigbench/contextual_parametric_knowledge_conflicts",
679
- "bigbench/conceptual_combinations",
680
- "bigbench/temporal_sequences",
681
- "bigbench/english_proverbs",
682
- "bigbench/gre_reading_comprehension",
683
- "bigbench/suicide_risk",
684
- "bigbench/emojis_emotion_prediction",
685
- "bigbench/phrase_relatedness",
 
 
 
686
  "bigbench/understanding_fables",
687
- "bigbench/riddle_sense",
688
- "bigbench/ruin_names",
689
- "bigbench/physics",
690
- "bigbench/reasoning_about_colored_objects",
691
  "bigbench/timedial",
692
- "bigbench/hhh_alignment",
693
- "bigbench/nonsense_words_grammar",
694
- "bigbench/crass_ai",
695
- "bigbench/undo_permutation",
696
- "bigbench/simple_ethical_questions",
697
- "bigbench/movie_recommendation",
698
- "bigbench/crash_blossom",
699
- "bigbench/entailed_polarity",
700
- "bigbench/goal_step_wikihow",
701
- "bigbench/key_value_maps",
702
- "bigbench/real_or_fake_text",
703
- "bigbench/human_organs_senses",
704
- "bigbench/logic_grid_puzzle",
705
- "bigbench/implicatures",
706
- "bigbench/similarities_abstraction",
707
- "bigbench/movie_dialog_same_or_different",
708
  "cos_e/v1.0",
709
  "cosmos_qa",
710
  "dream",
@@ -743,7 +747,6 @@
743
  "rumoureval_2019/RumourEval2019",
744
  "ethos/binary",
745
  "ethos/multilabel",
746
- "tweet_eval/hate",
747
  "tweet_eval/emotion",
748
  "tweet_eval/irony",
749
  "tweet_eval/offensive",
@@ -754,35 +757,36 @@
754
  "tweet_eval/stance_feminist",
755
  "tweet_eval/stance_hillary",
756
  "tweet_eval/emoji",
 
757
  "discovery/discovery",
758
- "pragmeval/squinky-formality",
759
  "pragmeval/emobank-valence",
 
760
  "pragmeval/emobank-dominance",
 
 
761
  "pragmeval/squinky-implicature",
762
  "pragmeval/squinky-informativeness",
763
- "pragmeval/switchboard",
764
  "pragmeval/mrda",
765
  "pragmeval/verifiability",
766
- "pragmeval/emobank-arousal",
767
- "pragmeval/emergent",
768
- "pragmeval/stac",
769
- "pragmeval/gum",
770
  "pragmeval/persuasiveness-claimtype",
771
  "pragmeval/persuasiveness-eloquence",
772
- "pragmeval/pdtb",
773
- "pragmeval/persuasiveness-relevance",
774
- "pragmeval/sarcasm",
775
  "pragmeval/persuasiveness-premisetype",
776
- "pragmeval/persuasiveness-strength",
 
777
  "pragmeval/persuasiveness-specificity",
778
- "silicone/dyda_e",
779
- "silicone/dyda_da",
780
- "silicone/meld_e",
781
- "silicone/meld_s",
782
- "silicone/oasis",
783
  "silicone/sem",
 
 
 
784
  "silicone/maptask",
785
- "silicone/iemocap",
 
786
  "lex_glue/eurlex",
787
  "lex_glue/scotus",
788
  "lex_glue/ledgar",
@@ -812,29 +816,29 @@
812
  "go_emotions/simplified",
813
  "scicite",
814
  "liar",
815
- "lexical_relation_classification/CogALexV",
816
  "lexical_relation_classification/EVALution",
817
  "lexical_relation_classification/ROOT09",
818
- "lexical_relation_classification/BLESS",
819
  "lexical_relation_classification/K&H+N",
820
  "linguisticprobing/bigram_shift",
821
  "linguisticprobing/top_constituents",
822
- "linguisticprobing/sentence_length",
823
  "linguisticprobing/subj_number",
824
- "linguisticprobing/obj_number",
825
- "linguisticprobing/past_present",
826
  "linguisticprobing/odd_man_out",
827
  "linguisticprobing/coordination_inversion",
 
 
 
828
  "linguisticprobing/tree_depth",
829
  "crowdflower/tweet_global_warming",
830
- "crowdflower/political-media-audience",
831
- "crowdflower/economic-news",
832
- "crowdflower/sentiment_nuclear_power",
833
  "crowdflower/political-media-message",
834
  "crowdflower/political-media-bias",
835
- "crowdflower/corporate-messaging",
836
  "crowdflower/airline-sentiment",
837
- "crowdflower/text_emotion",
 
 
 
838
  "ethics/commonsense",
839
  "ethics/deontology",
840
  "ethics/justice",
@@ -899,8 +903,8 @@
899
  "scruples",
900
  "wouldyourather",
901
  "attempto-nli",
902
- "defeasible-nli/atomic",
903
  "defeasible-nli/snli",
 
904
  "help-nli",
905
  "nli-veridicality-transitivity",
906
  "natural-language-satisfiability",
@@ -923,8 +927,8 @@
923
  "redefine-math",
924
  "puzzte",
925
  "implicatures",
926
- "race/high",
927
  "race/middle",
 
928
  "race-c",
929
  "spartqa-yn",
930
  "spartqa-mchoice",
@@ -950,10 +954,10 @@
950
  "oasst1_dense_flat/helpfulness",
951
  "PARARULE-Plus",
952
  "mindgames",
953
- "universal_dependencies/en_ewt/deprel",
954
  "universal_dependencies/en_gum/deprel",
955
- "universal_dependencies/en_lines/deprel",
956
  "universal_dependencies/en_partut/deprel",
 
957
  "ambient",
958
  "path-naturalness-prediction",
959
  "civil_comments/toxicity",
@@ -1012,7 +1016,11 @@
1012
  "lsat_qa/all",
1013
  "apt",
1014
  "twitter-financial-news-sentiment",
 
1015
  "SpaceNLI",
 
 
 
1016
  "babi_nli",
1017
  "gen_debiased_nli",
1018
  "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,
 
487
  1,
488
  2,
489
  3,
490
+ 2,
491
  3,
492
+ 3,
493
+ 2,
494
+ 2,
495
  2,
496
  3,
497
  3,
 
609
  "model-written-evals",
610
  "truthful_qa/multiple_choice",
611
  "fig-qa",
612
+ "bigbench/mathematical_induction",
 
 
 
 
 
 
 
 
613
  "bigbench/penguins_in_a_table",
614
+ "bigbench/strategyqa",
 
 
 
 
 
 
615
  "bigbench/dark_humor_detection",
616
+ "bigbench/social_support",
617
+ "bigbench/crass_ai",
618
+ "bigbench/real_or_fake_text",
619
+ "bigbench/symbol_interpretation",
620
+ "bigbench/tracking_shuffled_objects",
621
  "bigbench/fantasy_reasoning",
622
+ "bigbench/cause_and_effect",
623
+ "bigbench/dyck_languages",
624
+ "bigbench/known_unknowns",
625
  "bigbench/odd_one_out",
626
+ "bigbench/cs_algorithms",
627
+ "bigbench/crash_blossom",
628
+ "bigbench/nonsense_words_grammar",
629
+ "bigbench/snarks",
630
+ "bigbench/cifar10_classification",
631
+ "bigbench/emojis_emotion_prediction",
632
+ "bigbench/contextual_parametric_knowledge_conflicts",
633
+ "bigbench/checkmate_in_one",
634
+ "bigbench/metaphor_understanding",
635
+ "bigbench/evaluating_information_essentiality",
636
+ "bigbench/international_phonetic_alphabet_nli",
637
+ "bigbench/temporal_sequences",
638
+ "bigbench/authorship_verification",
639
+ "bigbench/logical_fallacy_detection",
640
+ "bigbench/anachronisms",
641
+ "bigbench/fact_checker",
642
+ "bigbench/analytic_entailment",
643
+ "bigbench/english_proverbs",
644
+ "bigbench/strange_stories",
645
+ "bigbench/identify_math_theorems",
646
+ "bigbench/conceptual_combinations",
647
+ "bigbench/mnist_ascii",
648
+ "bigbench/goal_step_wikihow",
649
  "bigbench/epistemic_reasoning",
650
+ "bigbench/implicatures",
 
651
  "bigbench/question_selection",
652
+ "bigbench/suicide_risk",
653
+ "bigbench/reasoning_about_colored_objects",
654
+ "bigbench/riddle_sense",
655
+ "bigbench/formal_fallacies_syllogisms_negation",
656
+ "bigbench/entailed_polarity",
657
+ "bigbench/winowhy",
658
+ "bigbench/movie_recommendation",
659
+ "bigbench/empirical_judgments",
660
  "bigbench/geometric_shapes",
661
+ "bigbench/moral_permissibility",
662
+ "bigbench/presuppositions_as_nli",
663
+ "bigbench/social_iqa",
664
+ "bigbench/undo_permutation",
665
+ "bigbench/intent_recognition",
666
+ "bigbench/phrase_relatedness",
667
+ "bigbench/similarities_abstraction",
668
  "bigbench/elementary_math_qa",
 
 
 
 
 
669
  "bigbench/novel_concepts",
670
+ "bigbench/play_dialog_same_or_different",
671
+ "bigbench/key_value_maps",
672
+ "bigbench/figure_of_speech_detection",
673
+ "bigbench/metaphor_boolean",
674
+ "bigbench/date_understanding",
675
+ "bigbench/simple_ethical_questions",
676
+ "bigbench/emoji_movie",
677
+ "bigbench/ruin_names",
678
+ "bigbench/abstract_narrative_understanding",
679
+ "bigbench/physics",
680
  "bigbench/misconceptions",
681
+ "bigbench/movie_dialog_same_or_different",
682
+ "bigbench/identify_odd_metaphor",
683
+ "bigbench/navigate",
684
  "bigbench/salient_translation_error_detection",
685
+ "bigbench/causal_judgment",
686
+ "bigbench/code_line_description",
687
+ "bigbench/gre_reading_comprehension",
688
  "bigbench/logical_deduction",
 
 
 
 
 
689
  "bigbench/hindu_knowledge",
690
+ "bigbench/physical_intuition",
691
+ "bigbench/color",
 
 
 
 
 
 
 
 
 
 
 
692
  "bigbench/unit_interpretation",
693
+ "bigbench/bbq_lite_json",
694
+ "bigbench/logic_grid_puzzle",
695
+ "bigbench/hhh_alignment",
696
  "bigbench/analogical_similarity",
697
+ "bigbench/implicit_relations",
698
+ "bigbench/vitaminc_fact_verification",
699
+ "bigbench/human_organs_senses",
700
+ "bigbench/arithmetic",
701
+ "bigbench/discourse_marker_prediction",
702
+ "bigbench/general_knowledge",
703
+ "bigbench/hyperbaton",
704
+ "bigbench/logical_sequence",
705
+ "bigbench/disambiguation_qa",
706
+ "bigbench/sentence_ambiguity",
707
+ "bigbench/irony_identification",
708
+ "bigbench/sports_understanding",
709
  "bigbench/understanding_fables",
710
+ "bigbench/logical_args",
 
 
 
711
  "bigbench/timedial",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
712
  "cos_e/v1.0",
713
  "cosmos_qa",
714
  "dream",
 
747
  "rumoureval_2019/RumourEval2019",
748
  "ethos/binary",
749
  "ethos/multilabel",
 
750
  "tweet_eval/emotion",
751
  "tweet_eval/irony",
752
  "tweet_eval/offensive",
 
757
  "tweet_eval/stance_feminist",
758
  "tweet_eval/stance_hillary",
759
  "tweet_eval/emoji",
760
+ "tweet_eval/hate",
761
  "discovery/discovery",
 
762
  "pragmeval/emobank-valence",
763
+ "pragmeval/switchboard",
764
  "pragmeval/emobank-dominance",
765
+ "pragmeval/emobank-arousal",
766
+ "pragmeval/squinky-formality",
767
  "pragmeval/squinky-implicature",
768
  "pragmeval/squinky-informativeness",
 
769
  "pragmeval/mrda",
770
  "pragmeval/verifiability",
771
+ "pragmeval/pdtb",
 
 
 
772
  "pragmeval/persuasiveness-claimtype",
773
  "pragmeval/persuasiveness-eloquence",
 
 
 
774
  "pragmeval/persuasiveness-premisetype",
775
+ "pragmeval/gum",
776
+ "pragmeval/stac",
777
  "pragmeval/persuasiveness-specificity",
778
+ "pragmeval/persuasiveness-strength",
779
+ "pragmeval/sarcasm",
780
+ "pragmeval/persuasiveness-relevance",
781
+ "pragmeval/emergent",
782
+ "silicone/iemocap",
783
  "silicone/sem",
784
+ "silicone/oasis",
785
+ "silicone/meld_s",
786
+ "silicone/meld_e",
787
  "silicone/maptask",
788
+ "silicone/dyda_e",
789
+ "silicone/dyda_da",
790
  "lex_glue/eurlex",
791
  "lex_glue/scotus",
792
  "lex_glue/ledgar",
 
816
  "go_emotions/simplified",
817
  "scicite",
818
  "liar",
819
+ "lexical_relation_classification/BLESS",
820
  "lexical_relation_classification/EVALution",
821
  "lexical_relation_classification/ROOT09",
822
+ "lexical_relation_classification/CogALexV",
823
  "lexical_relation_classification/K&H+N",
824
  "linguisticprobing/bigram_shift",
825
  "linguisticprobing/top_constituents",
 
826
  "linguisticprobing/subj_number",
 
 
827
  "linguisticprobing/odd_man_out",
828
  "linguisticprobing/coordination_inversion",
829
+ "linguisticprobing/obj_number",
830
+ "linguisticprobing/past_present",
831
+ "linguisticprobing/sentence_length",
832
  "linguisticprobing/tree_depth",
833
  "crowdflower/tweet_global_warming",
834
+ "crowdflower/text_emotion",
 
 
835
  "crowdflower/political-media-message",
836
  "crowdflower/political-media-bias",
 
837
  "crowdflower/airline-sentiment",
838
+ "crowdflower/sentiment_nuclear_power",
839
+ "crowdflower/political-media-audience",
840
+ "crowdflower/economic-news",
841
+ "crowdflower/corporate-messaging",
842
  "ethics/commonsense",
843
  "ethics/deontology",
844
  "ethics/justice",
 
903
  "scruples",
904
  "wouldyourather",
905
  "attempto-nli",
 
906
  "defeasible-nli/snli",
907
+ "defeasible-nli/atomic",
908
  "help-nli",
909
  "nli-veridicality-transitivity",
910
  "natural-language-satisfiability",
 
927
  "redefine-math",
928
  "puzzte",
929
  "implicatures",
 
930
  "race/middle",
931
+ "race/high",
932
  "race-c",
933
  "spartqa-yn",
934
  "spartqa-mchoice",
 
954
  "oasst1_dense_flat/helpfulness",
955
  "PARARULE-Plus",
956
  "mindgames",
 
957
  "universal_dependencies/en_gum/deprel",
958
+ "universal_dependencies/en_ewt/deprel",
959
  "universal_dependencies/en_partut/deprel",
960
+ "universal_dependencies/en_lines/deprel",
961
  "ambient",
962
  "path-naturalness-prediction",
963
  "civil_comments/toxicity",
 
1016
  "lsat_qa/all",
1017
  "apt",
1018
  "twitter-financial-news-sentiment",
1019
+ "icl-symbol-tuning-instruct",
1020
  "SpaceNLI",
1021
+ "propsegment/nli",
1022
+ "HatemojiBuild",
1023
+ "regset",
1024
  "babi_nli",
1025
  "gen_debiased_nli",
1026
  "imppres/presupposition",
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc7a150f04b55cf0740b9ab332e6adf1634b23f7bf5aab69d8f3d0c5c87e0efd
3
  size 1740400377
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40e81d769bb3606dbffbdddf48cd39cf5945e30bcad841cb100e70cf4258a756
3
  size 1740400377