Upload DebertaV2ForSequenceClassification

config.json

@@ -31,8 +31,8 @@
     2,
     2,
     2,
-    6,
     2,
+    6,
     2,
     2,
     2,
@@ -46,12 +46,10 @@
     3,
     3,
     2,
-    3,
     2,
     2,
     2,
-    3,
-    3,
+    5,
     3,
     3,
     3,
@@ -62,12 +60,6 @@
     3,
     2,
     2,
-    3,
-    3,
-    3,
-    3,
-    3,
-    3,
     2,
     3,
     3,
@@ -77,23 +69,6 @@
     3,
     3,
     3,
-    3,
-    3,
-    3,
-    3,
-    3,
-    3,
-    3,
-    3,
-    3,
-    3,
-    3,
-    3,
-    3,
-    3,
-    3,
-    3,
-    2,
     2,
     2,
     2,
@@ -243,45 +218,45 @@
     4,
     2,
     8,
-    3,
-    3,
+    2,
+    4,
     2,
     2,
     3,
     3,
-    20,
-    4,
     3,
-    2,
     3,
-    174,
     3,
-    51,
-    41,
+    3,
+    20,
+    174,
     2,
     2,
     2,
     2,
     2,
+    41,
+    51,
+    3,
     2,
+    3,
     18,
+    17,
+    3,
     2,
+    16,
     2,
     2,
     8,
     2,
-    3,
-    16,
-    17,
-    3,
     2,
+    7,
+    4,
+    7,
+    3,
     42,
     3,
-    7,
     12,
-    3,
-    7,
-    4,
     11,
     100,
     13,
@@ -303,7 +278,6 @@
     1,
     3,
     10,
-    77,
     3,
     10,
     4,
@@ -313,33 +287,33 @@
     28,
     3,
     6,
-    6,
     5,
     7,
-    4,
     3,
     6,
+    4,
+    2,
+    20,
+    6,
     2,
     2,
     2,
-    20,
-    7,
     2,
     2,
+    7,
     2,
     2,
     3,
     4,
-    3,
+    9,
     2,
     4,
-    9,
+    3,
     13,
     2,
     2,
     2,
     2,
-    2,
     4,
     1,
     2,
@@ -365,12 +339,6 @@
     3,
     2,
     2,
-    2,
-    2,
-    2,
-    3,
-    2,
-    2,
     12,
     3,
     3,
@@ -378,7 +346,6 @@
     19,
     3,
     1,
-    1,
     2,
     2,
     2,
@@ -411,6 +378,7 @@
     2,
     2,
     2,
+    2,
     3,
     2,
     2,
@@ -453,6 +421,78 @@
     3,
     2,
     1,
+    1,
+    1,
+    2,
+    2,
+    50,
+    50,
+    50,
+    50,
+    2,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    2,
+    2,
+    2,
+    2,
+    77,
+    2,
+    1,
+    3,
+    2,
+    2,
+    1,
+    1,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    3,
+    18,
+    13,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2,
+    4,
+    2,
+    24,
+    23,
+    67,
+    279,
+    3,
+    2,
+    2,
+    1,
+    2,
+    2,
+    3,
+    1,
+    2,
+    3,
+    3,
+    2,
+    3,
+    3,
+    3,
+    1,
     1
   ],
   "hidden_act": "gelu",
@@ -512,14 +552,14 @@
     "scitail/snli_format",
     "hans",
     "WANLI",
-    "recast/recast_verbnet",
     "recast/recast_ner",
-    "recast/recast_factuality",
+    "recast/recast_sentiment",
+    "recast/recast_megaveridicality",
+    "recast/recast_verbnet",
     "recast/recast_puns",
     "recast/recast_kg_relations",
-    "recast/recast_megaveridicality",
     "recast/recast_verbcorner",
-    "recast/recast_sentiment",
+    "recast/recast_factuality",
     "probability_words_nli/usnli",
     "probability_words_nli/reasoning_2hop",
     "probability_words_nli/reasoning_1hop",
@@ -531,12 +571,10 @@
     "dialogue_nli",
     "mpe",
     "dnc",
-    "gpt3_nli",
     "recast_white/fnplus",
     "recast_white/sprl",
     "recast_white/dpr",
     "joci",
-    "contrast_nli",
     "robust_nli/IS_CS",
     "robust_nli/LI_LI",
     "robust_nli/ST_WO",
@@ -547,41 +585,18 @@
     "robust_nli/ST_LM",
     "robust_nli_is_sd",
     "robust_nli_li_ts",
-    "gen_debiased_nli/snli_seq_z",
-    "gen_debiased_nli/snli_z_aug",
-    "gen_debiased_nli/snli_par_z",
-    "gen_debiased_nli/mnli_par_z",
-    "gen_debiased_nli/mnli_z_aug",
-    "gen_debiased_nli/mnli_seq_z",
     "add_one_rte",
-    "imppres/presupposition_only_presupposition/presupposition",
-    "imppres/presupposition_question_presupposition/presupposition",
-    "imppres/presupposition_cleft_uniqueness/presupposition",
-    "imppres/presupposition_both_presupposition/presupposition",
-    "imppres/presupposition_all_n_presupposition/presupposition",
-    "imppres/presupposition_change_of_state/presupposition",
-    "imppres/presupposition_possessed_definites_existence/presupposition",
-    "imppres/presupposition_possessed_definites_uniqueness/presupposition",
-    "imppres/presupposition_cleft_existence/presupposition",
-    "imppres/implicature_numerals_2_3/prag",
-    "imppres/implicature_connectives/prag",
-    "imppres/implicature_gradable_adjective/prag",
-    "imppres/implicature_gradable_verb/prag",
-    "imppres/implicature_modals/prag",
-    "imppres/implicature_numerals_10_100/prag",
-    "imppres/implicature_quantifiers/prag",
     "imppres/implicature_gradable_verb/log",
-    "imppres/implicature_modals/log",
-    "imppres/implicature_numerals_10_100/log",
-    "imppres/implicature_numerals_2_3/log",
     "imppres/implicature_quantifiers/log",
     "imppres/implicature_connectives/log",
+    "imppres/implicature_numerals_2_3/log",
+    "imppres/implicature_numerals_10_100/log",
     "imppres/implicature_gradable_adjective/log",
+    "imppres/implicature_modals/log",
     "glue_diagnostics/diagnostics",
     "hlgd",
     "paws/labeled_final",
     "paws/labeled_swap",
-    "quora",
     "medical_questions_pairs",
     "conll2003/pos_tags",
     "conll2003/chunk_tags",
@@ -590,106 +605,106 @@
     "model-written-evals",
     "truthful_qa/multiple_choice",
     "fig-qa",
-    "bigbench/entailed_polarity",
-    "bigbench/logical_args",
-    "bigbench/sports_understanding",
-    "bigbench/color",
-    "bigbench/goal_step_wikihow",
-    "bigbench/fantasy_reasoning",
-    "bigbench/navigate",
-    "bigbench/known_unknowns",
-    "bigbench/real_or_fake_text",
-    "bigbench/novel_concepts",
     "bigbench/logical_sequence",
-    "bigbench/crass_ai",
-    "bigbench/identify_odd_metaphor",
-    "bigbench/arithmetic",
-    "bigbench/elementary_math_qa",
-    "bigbench/cifar10_classification",
-    "bigbench/riddle_sense",
-    "bigbench/salient_translation_error_detection",
-    "bigbench/tracking_shuffled_objects",
+    "bigbench/snarks",
+    "bigbench/general_knowledge",
+    "bigbench/moral_permissibility",
+    "bigbench/figure_of_speech_detection",
+    "bigbench/abstract_narrative_understanding",
+    "bigbench/anachronisms",
+    "bigbench/vitaminc_fact_verification",
+    "bigbench/authorship_verification",
+    "bigbench/penguins_in_a_table",
+    "bigbench/play_dialog_same_or_different",
+    "bigbench/physical_intuition",
+    "bigbench/empirical_judgments",
+    "bigbench/checkmate_in_one",
+    "bigbench/metaphor_understanding",
+    "bigbench/cs_algorithms",
+    "bigbench/dyck_languages",
     "bigbench/dark_humor_detection",
-    "bigbench/mathematical_induction",
-    "bigbench/implicit_relations",
-    "bigbench/logic_grid_puzzle",
-    "bigbench/analytic_entailment",
-    "bigbench/temporal_sequences",
-    "bigbench/question_selection",
+    "bigbench/fantasy_reasoning",
     "bigbench/odd_one_out",
-    "bigbench/international_phonetic_alphabet_nli",
-    "bigbench/nonsense_words_grammar",
-    "bigbench/play_dialog_same_or_different",
-    "bigbench/winowhy",
-    "bigbench/causal_judgment",
+    "bigbench/epistemic_reasoning",
+    "bigbench/identify_odd_metaphor",
+    "bigbench/discourse_marker_prediction",
+    "bigbench/question_selection",
+    "bigbench/geometric_shapes",
+    "bigbench/date_understanding",
     "bigbench/disambiguation_qa",
-    "bigbench/conceptual_combinations",
+    "bigbench/strategyqa",
+    "bigbench/color",
+    "bigbench/elementary_math_qa",
+    "bigbench/mathematical_induction",
+    "bigbench/strange_stories",
+    "bigbench/logical_args",
+    "bigbench/cifar10_classification",
     "bigbench/evaluating_information_essentiality",
-    "bigbench/code_line_description",
-    "bigbench/physics",
-    "bigbench/moral_permissibility",
-    "bigbench/ruin_names",
-    "bigbench/misconceptions",
-    "bigbench/general_knowledge",
-    "bigbench/phrase_relatedness",
-    "bigbench/unit_interpretation",
-    "bigbench/contextual_parametric_knowledge_conflicts",
+    "bigbench/novel_concepts",
+    "bigbench/hyperbaton",
     "bigbench/fact_checker",
+    "bigbench/sentence_ambiguity",
+    "bigbench/social_iqa",
     "bigbench/identify_math_theorems",
-    "bigbench/logical_fallacy_detection",
-    "bigbench/suicide_risk",
     "bigbench/cause_and_effect",
-    "bigbench/timedial",
-    "bigbench/key_value_maps",
+    "bigbench/misconceptions",
+    "bigbench/causal_judgment",
+    "bigbench/international_phonetic_alphabet_nli",
+    "bigbench/implicit_relations",
+    "bigbench/salient_translation_error_detection",
+    "bigbench/logical_deduction",
+    "bigbench/known_unknowns",
+    "bigbench/arithmetic",
+    "bigbench/sports_understanding",
+    "bigbench/navigate",
     "bigbench/irony_identification",
-    "bigbench/emojis_emotion_prediction",
-    "bigbench/reasoning_about_colored_objects",
     "bigbench/hindu_knowledge",
-    "bigbench/authorship_verification",
-    "bigbench/human_organs_senses",
     "bigbench/mnist_ascii",
-    "bigbench/epistemic_reasoning",
-    "bigbench/metaphor_boolean",
-    "bigbench/strategyqa",
-    "bigbench/intent_recognition",
-    "bigbench/metaphor_understanding",
-    "bigbench/movie_recommendation",
-    "bigbench/sentence_ambiguity",
-    "bigbench/hhh_alignment",
-    "bigbench/emoji_movie",
-    "bigbench/geometric_shapes",
-    "bigbench/social_iqa",
-    "bigbench/abstract_narrative_understanding",
-    "bigbench/penguins_in_a_table",
-    "bigbench/anachronisms",
+    "bigbench/social_support",
+    "bigbench/presuppositions_as_nli",
+    "bigbench/tracking_shuffled_objects",
+    "bigbench/winowhy",
     "bigbench/formal_fallacies_syllogisms_negation",
-    "bigbench/strange_stories",
-    "bigbench/cs_algorithms",
-    "bigbench/physical_intuition",
-    "bigbench/simple_ethical_questions",
-    "bigbench/similarities_abstraction",
-    "bigbench/symbol_interpretation",
+    "bigbench/emoji_movie",
+    "bigbench/code_line_description",
+    "bigbench/logical_fallacy_detection",
+    "bigbench/intent_recognition",
     "bigbench/bbq_lite_json",
-    "bigbench/movie_dialog_same_or_different",
-    "bigbench/dyck_languages",
+    "bigbench/metaphor_boolean",
+    "bigbench/analytic_entailment",
+    "bigbench/unit_interpretation",
     "bigbench/analogical_similarity",
-    "bigbench/logical_deduction",
-    "bigbench/snarks",
-    "bigbench/social_support",
-    "bigbench/empirical_judgments",
-    "bigbench/date_understanding",
-    "bigbench/presuppositions_as_nli",
-    "bigbench/implicatures",
-    "bigbench/vitaminc_fact_verification",
-    "bigbench/checkmate_in_one",
-    "bigbench/gre_reading_comprehension",
-    "bigbench/undo_permutation",
+    "bigbench/symbol_interpretation",
+    "bigbench/contextual_parametric_knowledge_conflicts",
+    "bigbench/conceptual_combinations",
+    "bigbench/temporal_sequences",
     "bigbench/english_proverbs",
-    "bigbench/discourse_marker_prediction",
+    "bigbench/gre_reading_comprehension",
+    "bigbench/suicide_risk",
+    "bigbench/emojis_emotion_prediction",
+    "bigbench/phrase_relatedness",
     "bigbench/understanding_fables",
-    "bigbench/figure_of_speech_detection",
-    "bigbench/hyperbaton",
+    "bigbench/riddle_sense",
+    "bigbench/ruin_names",
+    "bigbench/physics",
+    "bigbench/reasoning_about_colored_objects",
+    "bigbench/timedial",
+    "bigbench/hhh_alignment",
+    "bigbench/nonsense_words_grammar",
+    "bigbench/crass_ai",
+    "bigbench/undo_permutation",
+    "bigbench/simple_ethical_questions",
+    "bigbench/movie_recommendation",
     "bigbench/crash_blossom",
+    "bigbench/entailed_polarity",
+    "bigbench/goal_step_wikihow",
+    "bigbench/key_value_maps",
+    "bigbench/real_or_fake_text",
+    "bigbench/human_organs_senses",
+    "bigbench/logic_grid_puzzle",
+    "bigbench/implicatures",
+    "bigbench/similarities_abstraction",
+    "bigbench/movie_dialog_same_or_different",
     "cos_e/v1.0",
     "cosmos_qa",
     "dream",
@@ -700,7 +715,7 @@
     "head_qa/en",
     "sciq",
     "social_i_qa",
-    "wiki_hop",
+    "wiki_hop/original",
     "wiqa",
     "piqa",
     "hellaswag",
@@ -713,7 +728,7 @@
     "ai2_arc/ARC-Challenge/challenge",
     "ai2_arc/ARC-Easy/challenge",
     "definite_pronoun_resolution",
-    "swag",
+    "swag/regular",
     "math_qa",
     "glue/cola",
     "glue/sst2",
@@ -728,45 +743,45 @@
     "rumoureval_2019/RumourEval2019",
     "ethos/binary",
     "ethos/multilabel",
-    "tweet_eval/stance_feminist",
-    "tweet_eval/stance_climate",
+    "tweet_eval/hate",
+    "tweet_eval/emotion",
     "tweet_eval/irony",
     "tweet_eval/offensive",
     "tweet_eval/sentiment",
+    "tweet_eval/stance_abortion",
+    "tweet_eval/stance_atheism",
+    "tweet_eval/stance_climate",
+    "tweet_eval/stance_feminist",
     "tweet_eval/stance_hillary",
     "tweet_eval/emoji",
-    "tweet_eval/emotion",
-    "tweet_eval/stance_atheism",
-    "tweet_eval/hate",
-    "tweet_eval/stance_abortion",
     "discovery/discovery",
-    "pragmeval/verifiability",
-    "pragmeval/mrda",
-    "pragmeval/switchboard",
-    "pragmeval/emobank-arousal",
-    "pragmeval/emobank-dominance",
-    "pragmeval/squinky-informativeness",
-    "pragmeval/squinky-implicature",
     "pragmeval/squinky-formality",
     "pragmeval/emobank-valence",
+    "pragmeval/emobank-dominance",
+    "pragmeval/squinky-implicature",
+    "pragmeval/squinky-informativeness",
+    "pragmeval/switchboard",
+    "pragmeval/mrda",
+    "pragmeval/verifiability",
+    "pragmeval/emobank-arousal",
+    "pragmeval/emergent",
     "pragmeval/stac",
-    "pragmeval/persuasiveness-strength",
-    "pragmeval/persuasiveness-specificity",
-    "pragmeval/persuasiveness-relevance",
-    "pragmeval/persuasiveness-premisetype",
-    "pragmeval/persuasiveness-eloquence",
+    "pragmeval/gum",
     "pragmeval/persuasiveness-claimtype",
+    "pragmeval/persuasiveness-eloquence",
     "pragmeval/pdtb",
-    "pragmeval/gum",
-    "pragmeval/emergent",
+    "pragmeval/persuasiveness-relevance",
     "pragmeval/sarcasm",
-    "silicone/oasis",
-    "silicone/meld_s",
-    "silicone/meld_e",
-    "silicone/maptask",
-    "silicone/sem",
+    "pragmeval/persuasiveness-premisetype",
+    "pragmeval/persuasiveness-strength",
+    "pragmeval/persuasiveness-specificity",
     "silicone/dyda_e",
     "silicone/dyda_da",
+    "silicone/meld_e",
+    "silicone/meld_s",
+    "silicone/oasis",
+    "silicone/sem",
+    "silicone/maptask",
     "silicone/iemocap",
     "lex_glue/eurlex",
     "lex_glue/scotus",
@@ -788,7 +803,6 @@
     "humicroedit/subtask-1",
     "humicroedit/subtask-2",
     "snips_built_in_intents",
-    "banking77",
     "hate_speech_offensive",
     "yahoo_answers_topics",
     "stackoverflow-questions",
@@ -798,29 +812,29 @@
     "go_emotions/simplified",
     "scicite",
     "liar",
-    "lexical_relation_classification/BLESS",
     "lexical_relation_classification/CogALexV",
     "lexical_relation_classification/EVALution",
-    "lexical_relation_classification/K&H+N",
     "lexical_relation_classification/ROOT09",
-    "linguisticprobing/sentence_length",
+    "lexical_relation_classification/BLESS",
+    "lexical_relation_classification/K&H+N",
     "linguisticprobing/bigram_shift",
+    "linguisticprobing/top_constituents",
+    "linguisticprobing/sentence_length",
+    "linguisticprobing/subj_number",
+    "linguisticprobing/obj_number",
+    "linguisticprobing/past_present",
     "linguisticprobing/odd_man_out",
     "linguisticprobing/coordination_inversion",
-    "linguisticprobing/top_constituents",
     "linguisticprobing/tree_depth",
-    "linguisticprobing/past_present",
-    "linguisticprobing/obj_number",
-    "linguisticprobing/subj_number",
+    "crowdflower/tweet_global_warming",
     "crowdflower/political-media-audience",
     "crowdflower/economic-news",
-    "crowdflower/corporate-messaging",
-    "crowdflower/airline-sentiment",
-    "crowdflower/tweet_global_warming",
     "crowdflower/sentiment_nuclear_power",
     "crowdflower/political-media-message",
-    "crowdflower/text_emotion",
     "crowdflower/political-media-bias",
+    "crowdflower/corporate-messaging",
+    "crowdflower/airline-sentiment",
+    "crowdflower/text_emotion",
     "ethics/commonsense",
     "ethics/deontology",
     "ethics/justice",
@@ -846,12 +860,6 @@
     "discosense",
     "circa",
     "EffectiveFeedbackStudentWriting",
-    "promptSentiment",
-    "promptNLI",
-    "promptSpoke",
-    "promptProficiency",
-    "promptGrammar",
-    "promptCoherence",
     "phrase_similarity",
     "scientific-exaggeration-detection",
     "quarel",
@@ -863,7 +871,6 @@
     "sem_eval_2010_task_8",
     "auditor_review/demo-org--auditor_review",
     "medmcqa",
-    "aqua_rat/tokenized",
     "Dynasent_Disagreement",
     "Politeness_Disagreement",
     "SBIC_Disagreement",
@@ -892,8 +899,9 @@
     "scruples",
     "wouldyourather",
     "attempto-nli",
-    "defeasible-nli/snli",
     "defeasible-nli/atomic",
+    "defeasible-nli/snli",
+    "help-nli",
     "nli-veridicality-transitivity",
     "natural-language-satisfiability",
     "lonli",
@@ -936,12 +944,84 @@
     "implicit-hate-stg1",
     "chaos-mnli-ambiguity",
     "headline_cause/en_simple",
+    "logiqa-2.0-nli",
+    "oasst1_dense_flat/quality",
+    "oasst1_dense_flat/toxicity",
+    "oasst1_dense_flat/helpfulness",
+    "PARARULE-Plus",
+    "mindgames",
+    "universal_dependencies/en_ewt/deprel",
+    "universal_dependencies/en_gum/deprel",
+    "universal_dependencies/en_lines/deprel",
+    "universal_dependencies/en_partut/deprel",
+    "ambient",
+    "path-naturalness-prediction",
+    "civil_comments/toxicity",
+    "civil_comments/severe_toxicity",
+    "civil_comments/obscene",
+    "civil_comments/threat",
+    "civil_comments/insult",
+    "civil_comments/identity_attack",
+    "civil_comments/sexual_explicit",
+    "cloth",
+    "dgen",
+    "oasst1_pairwise_rlhf_reward",
+    "I2D2",
+    "args_me",
+    "Touche23-ValueEval",
+    "starcon",
+    "banking77",
+    "ruletaker",
+    "lsat_qa/all",
+    "ConTRoL-nli",
+    "tracie",
+    "sherliic",
+    "sen-making/1",
+    "sen-making/2",
+    "winowhy",
+    "mbib-base/cognitive-bias",
+    "mbib-base/fake-news",
+    "mbib-base/gender-bias",
+    "mbib-base/hate-speech",
+    "mbib-base/linguistic-bias",
+    "mbib-base/political-bias",
+    "mbib-base/racial-bias",
+    "mbib-base/text-level-bias",
+    "robustLR",
+    "v1/gen_train234_test2to10",
+    "logical-fallacy",
+    "parade",
+    "cladder",
+    "subjectivity",
+    "MOH",
+    "VUAC",
+    "TroFi",
+    "sharc_modified/mod",
+    "conceptrules_v2",
+    "disrpt/eng.dep.scidtb",
+    "conll2000",
+    "few-nerd/supervised",
+    "finer-139",
+    "zero-shot-label-nli",
+    "com2sense",
+    "scone",
+    "winodict",
+    "fool-me-twice",
+    "monli",
+    "corr2cause",
+    "lsat_qa/all",
+    "apt",
+    "twitter-financial-news-sentiment",
+    "SpaceNLI",
     "babi_nli",
+    "gen_debiased_nli",
+    "imppres/presupposition",
+    "/prag",
     "blimp-2",
     "mmlu-4"
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.26.0",
+  "transformers_version": "4.26.1",
   "type_vocab_size": 0,
   "vocab_size": 128100
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:706433291e04d0a5099445cda6c065dc027c17490f6e29b6375f5cb2e930c24c
+oid sha256:cc7a150f04b55cf0740b9ab332e6adf1634b23f7bf5aab69d8f3d0c5c87e0efd
 size 1740400377