Upload DebertaV2ForSequenceClassification

README.md

@@ -1,23 +1,4 @@
 ---
-license: apache-2.0
-language: en
-tags:
-- deberta-v3-small
-- deberta-v3
-- deberta
-- text-classification
-- nli
-- natural-language-inference
-- multitask
-- multi-task
-- pipeline
-- extreme-multi-task
-- extreme-mtl
-- tasksource
-- zero-shot
-- rlhf
-
-
 datasets:
 - nyu-mll/glue
 - super_glue
@@ -284,10 +265,27 @@ datasets:
 - tasksource/regset
 - tasksource/babi_nli
 - lmsys/chatbot_arena_conversations
+language: en
+library_name: transformers
+license: apache-2.0
 metrics:
 - accuracy
-library_name: transformers
 pipeline_tag: zero-shot-classification
+tags:
+- deberta-v3-small
+- deberta-v3
+- deberta
+- text-classification
+- nli
+- natural-language-inference
+- multitask
+- multi-task
+- pipeline
+- extreme-multi-task
+- extreme-mtl
+- tasksource
+- zero-shot
+- rlhf
 ---
 
 # Model Card for DeBERTa-v3-small-tasksource-nli

config.json

@@ -27,8 +27,8 @@
     2,
     2,
     3,
-    6,
     2,
+    6,
     2,
     2,
     2,
@@ -68,14 +68,10 @@
     3,
     3,
     3,
-    3,
     2,
     2,
     2,
     2,
-    47,
-    23,
-    9,
     1,
     1,
     1,
@@ -217,12 +213,12 @@
     4,
     2,
     8,
+    2,
     3,
-    4,
     2,
     2,
+    4,
     20,
-    2,
     3,
     3,
     3,
@@ -233,30 +229,30 @@
     2,
     2,
     2,
-    2,
     41,
+    3,
     51,
     2,
-    3,
     2,
     2,
-    18,
     2,
     16,
-    8,
-    3,
     17,
-    3,
+    18,
+    2,
     2,
     2,
+    3,
+    8,
+    3,
+    7,
+    7,
     11,
+    3,
+    3,
     42,
     12,
-    7,
-    3,
     4,
-    3,
-    7,
     100,
     13,
     100,
@@ -286,28 +282,28 @@
     28,
     3,
     6,
-    7,
-    6,
     5,
+    7,
     4,
+    6,
     3,
     2,
-    7,
+    2,
     2,
     6,
     2,
+    7,
+    20,
     2,
     2,
-    20,
+    4,
     2,
     9,
     13,
     4,
     2,
-    4,
     3,
     2,
-    2,
     3,
     2,
     2,
@@ -317,11 +313,6 @@
     1,
     2,
     1,
-    13,
-    3,
-    5,
-    11,
-    37,
     2,
     49,
     40,
@@ -370,8 +361,6 @@
     1,
     2,
     1,
-    3,
-    2,
     2,
     2,
     2,
@@ -421,10 +410,6 @@
     1,
     1,
     2,
-    50,
-    50,
-    50,
-    50,
     2,
     1,
     1,
@@ -441,21 +426,12 @@
     2,
     2,
     77,
-    1,
     3,
     2,
     2,
     1,
     1,
     2,
-    2,
-    2,
-    2,
-    2,
-    2,
-    2,
-    2,
-    2,
     3,
     18,
     13,
@@ -464,13 +440,9 @@
     2,
     2,
     2,
-    2,
     4,
     2,
     24,
-    23,
-    67,
-    279,
     3,
     2,
     2,
@@ -490,6 +462,7 @@
     1,
     17,
     3,
+    3,
     2,
     3,
     2,
@@ -511,11 +484,56 @@
     2,
     3,
     2,
+    3,
+    4,
+    3,
+    3,
+    2,
+    1,
+    1,
+    2,
+    1,
+    1,
+    6,
     2,
     3,
     3,
+    1,
+    1,
+    2,
+    2,
+    10,
+    2,
+    2,
+    2,
+    5,
+    5,
+    5,
+    5,
+    5,
+    5,
+    5,
+    5,
+    5,
+    5,
+    4,
+    1,
+    7,
+    6,
+    6,
+    6,
+    6,
+    6,
+    6,
     3,
+    2,
     1,
+    2,
+    2,
+    2,
+    3,
+    3,
+    3,
     1
   ],
   "hidden_act": "gelu",
@@ -534,7 +552,7 @@
     "neutral": 1
   },
   "layer_norm_eps": 1e-07,
-  "max_position_embeddings": 512,
+  "max_position_embeddings": 1680,
   "max_relative_positions": -1,
   "model_type": "deberta-v2",
   "norm_rel_ebd": "layer_norm",
@@ -575,18 +593,18 @@
     "scitail/snli_format",
     "hans",
     "WANLI",
-    "recast/recast_kg_relations",
-    "recast/recast_megaveridicality",
     "recast/recast_ner",
-    "recast/recast_verbcorner",
-    "recast/recast_factuality",
-    "recast/recast_verbnet",
+    "recast/recast_kg_relations",
     "recast/recast_puns",
+    "recast/recast_verbcorner",
     "recast/recast_sentiment",
+    "recast/recast_verbnet",
+    "recast/recast_factuality",
+    "recast/recast_megaveridicality",
     "probability_words_nli/reasoning_2hop",
     "probability_words_nli/reasoning_1hop",
     "probability_words_nli/usnli",
-    "nan-nli/joey234--nan-nli",
+    "nan-nli",
     "nli_fever",
     "breaking_nli",
     "conj_nli",
@@ -611,122 +629,118 @@
     "add_one_rte",
     "imppres/implicature_quantifiers/log",
     "imppres/implicature_numerals_2_3/log",
-    "imppres/implicature_modals/log",
     "imppres/implicature_gradable_adjective/log",
     "imppres/implicature_connectives/log",
+    "imppres/implicature_modals/log",
     "imppres/implicature_numerals_10_100/log",
     "imppres/implicature_gradable_verb/log",
-    "glue_diagnostics/diagnostics",
     "hlgd",
     "paws/labeled_final",
     "paws/labeled_swap",
     "medical_questions_pairs",
-    "conll2003/pos_tags",
-    "conll2003/chunk_tags",
-    "conll2003/ner_tags",
     "model-written-evals",
     "truthful_qa/multiple_choice",
     "fig-qa",
-    "bigbench/contextual_parametric_knowledge_conflicts",
-    "bigbench/empirical_judgments",
-    "bigbench/hhh_alignment",
-    "bigbench/metaphor_boolean",
-    "bigbench/key_value_maps",
-    "bigbench/known_unknowns",
-    "bigbench/symbol_interpretation",
-    "bigbench/misconceptions",
     "bigbench/bbq_lite_json",
-    "bigbench/navigate",
-    "bigbench/discourse_marker_prediction",
-    "bigbench/disambiguation_qa",
-    "bigbench/cifar10_classification",
-    "bigbench/real_or_fake_text",
-    "bigbench/moral_permissibility",
-    "bigbench/abstract_narrative_understanding",
-    "bigbench/physics",
+    "bigbench/english_proverbs",
+    "bigbench/figure_of_speech_detection",
+    "bigbench/emoji_movie",
+    "bigbench/date_understanding",
+    "bigbench/metaphor_understanding",
     "bigbench/logical_fallacy_detection",
-    "bigbench/code_line_description",
-    "bigbench/implicit_relations",
-    "bigbench/unit_interpretation",
-    "bigbench/logical_sequence",
+    "bigbench/analogical_similarity",
     "bigbench/mnist_ascii",
-    "bigbench/irony_identification",
-    "bigbench/mathematical_induction",
-    "bigbench/winowhy",
     "bigbench/elementary_math_qa",
-    "bigbench/implicatures",
-    "bigbench/vitaminc_fact_verification",
-    "bigbench/play_dialog_same_or_different",
-    "bigbench/movie_dialog_same_or_different",
-    "bigbench/physical_intuition",
-    "bigbench/reasoning_about_colored_objects",
-    "bigbench/english_proverbs",
-    "bigbench/timedial",
-    "bigbench/conceptual_combinations",
-    "bigbench/suicide_risk",
-    "bigbench/movie_recommendation",
-    "bigbench/formal_fallacies_syllogisms_negation",
-    "bigbench/causal_judgment",
-    "bigbench/emoji_movie",
+    "bigbench/snarks",
+    "bigbench/social_support",
+    "bigbench/logical_deduction",
+    "bigbench/emojis_emotion_prediction",
     "bigbench/sports_understanding",
-    "bigbench/hindu_knowledge",
-    "bigbench/entailed_polarity",
-    "bigbench/fact_checker",
-    "bigbench/fantasy_reasoning",
-    "bigbench/logical_args",
-    "bigbench/evaluating_information_essentiality",
-    "bigbench/crass_ai",
-    "bigbench/identify_odd_metaphor",
-    "bigbench/cause_and_effect",
-    "bigbench/undo_permutation",
-    "bigbench/intent_recognition",
-    "bigbench/cs_algorithms",
-    "bigbench/identify_math_theorems",
+    "bigbench/cifar10_classification",
+    "bigbench/tracking_shuffled_objects",
+    "bigbench/physics",
+    "bigbench/mathematical_induction",
+    "bigbench/movie_dialog_same_or_different",
+    "bigbench/goal_step_wikihow",
     "bigbench/strategyqa",
-    "bigbench/penguins_in_a_table",
-    "bigbench/nonsense_words_grammar",
-    "bigbench/logical_deduction",
-    "bigbench/phrase_relatedness",
+    "bigbench/identify_math_theorems",
     "bigbench/gre_reading_comprehension",
-    "bigbench/understanding_fables",
-    "bigbench/question_selection",
-    "bigbench/ruin_names",
-    "bigbench/logic_grid_puzzle",
-    "bigbench/presuppositions_as_nli",
+    "bigbench/novel_concepts",
+    "bigbench/conceptual_combinations",
+    "bigbench/hyperbaton",
     "bigbench/strange_stories",
-    "bigbench/general_knowledge",
-    "bigbench/geometric_shapes",
-    "bigbench/social_support",
-    "bigbench/color",
-    "bigbench/snarks",
-    "bigbench/odd_one_out",
-    "bigbench/epistemic_reasoning",
-    "bigbench/emojis_emotion_prediction",
-    "bigbench/metaphor_understanding",
-    "bigbench/human_organs_senses",
+    "bigbench/contextual_parametric_knowledge_conflicts",
+    "bigbench/implicatures",
+    "bigbench/penguins_in_a_table",
+    "bigbench/logical_sequence",
     "bigbench/simple_ethical_questions",
+    "bigbench/dyck_languages",
+    "bigbench/geometric_shapes",
+    "bigbench/irony_identification",
+    "bigbench/intent_recognition",
+    "bigbench/logical_args",
+    "bigbench/known_unknowns",
+    "bigbench/formal_fallacies_syllogisms_negation",
+    "bigbench/suicide_risk",
     "bigbench/crash_blossom",
-    "bigbench/authorship_verification",
+    "bigbench/logic_grid_puzzle",
+    "bigbench/analytic_entailment",
     "bigbench/dark_humor_detection",
-    "bigbench/analogical_similarity",
-    "bigbench/social_iqa",
-    "bigbench/figure_of_speech_detection",
-    "bigbench/sentence_ambiguity",
+    "bigbench/timedial",
+    "bigbench/presuppositions_as_nli",
+    "bigbench/arithmetic",
+    "bigbench/implicit_relations",
+    "bigbench/understanding_fables",
     "bigbench/salient_translation_error_detection",
-    "bigbench/novel_concepts",
     "bigbench/anachronisms",
-    "bigbench/arithmetic",
-    "bigbench/riddle_sense",
-    "bigbench/analytic_entailment",
-    "bigbench/date_understanding",
-    "bigbench/dyck_languages",
-    "bigbench/tracking_shuffled_objects",
-    "bigbench/temporal_sequences",
-    "bigbench/hyperbaton",
-    "bigbench/goal_step_wikihow",
-    "bigbench/international_phonetic_alphabet_nli",
+    "bigbench/moral_permissibility",
+    "bigbench/abstract_narrative_understanding",
+    "bigbench/misconceptions",
+    "bigbench/nonsense_words_grammar",
+    "bigbench/code_line_description",
+    "bigbench/sentence_ambiguity",
+    "bigbench/disambiguation_qa",
+    "bigbench/crass_ai",
     "bigbench/similarities_abstraction",
+    "bigbench/authorship_verification",
+    "bigbench/phrase_relatedness",
+    "bigbench/color",
+    "bigbench/hhh_alignment",
+    "bigbench/metaphor_boolean",
+    "bigbench/fantasy_reasoning",
+    "bigbench/ruin_names",
+    "bigbench/cause_and_effect",
+    "bigbench/temporal_sequences",
+    "bigbench/navigate",
+    "bigbench/symbol_interpretation",
+    "bigbench/key_value_maps",
+    "bigbench/entailed_polarity",
+    "bigbench/riddle_sense",
+    "bigbench/discourse_marker_prediction",
+    "bigbench/reasoning_about_colored_objects",
+    "bigbench/empirical_judgments",
+    "bigbench/fact_checker",
+    "bigbench/movie_recommendation",
     "bigbench/checkmate_in_one",
+    "bigbench/epistemic_reasoning",
+    "bigbench/vitaminc_fact_verification",
+    "bigbench/general_knowledge",
+    "bigbench/identify_odd_metaphor",
+    "bigbench/physical_intuition",
+    "bigbench/winowhy",
+    "bigbench/cs_algorithms",
+    "bigbench/undo_permutation",
+    "bigbench/evaluating_information_essentiality",
+    "bigbench/unit_interpretation",
+    "bigbench/question_selection",
+    "bigbench/international_phonetic_alphabet_nli",
+    "bigbench/play_dialog_same_or_different",
+    "bigbench/real_or_fake_text",
+    "bigbench/human_organs_senses",
+    "bigbench/hindu_knowledge",
+    "bigbench/social_iqa",
+    "bigbench/odd_one_out",
+    "bigbench/causal_judgment",
     "cos_e/v1.0",
     "cosmos_qa",
     "dream",
@@ -760,51 +774,51 @@
     "toxic_conversations",
     "TuringBench",
     "trec",
-    "vitaminc/tals--vitaminc",
+    "vitaminc",
     "hope_edi/english",
     "rumoureval_2019/RumourEval2019",
     "ethos/binary",
     "ethos/multilabel",
+    "tweet_eval/offensive",
     "tweet_eval/sentiment",
-    "tweet_eval/emotion",
-    "tweet_eval/hate",
     "tweet_eval/irony",
+    "tweet_eval/hate",
+    "tweet_eval/emotion",
     "tweet_eval/emoji",
-    "tweet_eval/offensive",
     "tweet_eval/stance_abortion",
     "tweet_eval/stance_atheism",
     "tweet_eval/stance_climate",
     "tweet_eval/stance_feminist",
     "tweet_eval/stance_hillary",
     "discovery/discovery",
-    "pragmeval/squinky-informativeness",
-    "pragmeval/squinky-implicature",
-    "pragmeval/emobank-arousal",
     "pragmeval/squinky-formality",
-    "pragmeval/emobank-dominance",
+    "pragmeval/emobank-arousal",
+    "pragmeval/squinky-implicature",
+    "pragmeval/squinky-informativeness",
     "pragmeval/switchboard",
+    "pragmeval/verifiability",
     "pragmeval/mrda",
     "pragmeval/emobank-valence",
-    "pragmeval/verifiability",
+    "pragmeval/emobank-dominance",
     "pragmeval/persuasiveness-strength",
-    "pragmeval/sarcasm",
-    "pragmeval/stac",
     "pragmeval/persuasiveness-relevance",
     "pragmeval/pdtb",
-    "pragmeval/persuasiveness-premisetype",
-    "pragmeval/emergent",
     "pragmeval/gum",
-    "pragmeval/persuasiveness-claimtype",
-    "pragmeval/persuasiveness-eloquence",
+    "pragmeval/stac",
     "pragmeval/persuasiveness-specificity",
+    "pragmeval/sarcasm",
+    "pragmeval/persuasiveness-eloquence",
+    "pragmeval/emergent",
+    "pragmeval/persuasiveness-premisetype",
+    "pragmeval/persuasiveness-claimtype",
+    "silicone/meld_e",
+    "silicone/dyda_e",
     "silicone/iemocap",
+    "silicone/sem",
+    "silicone/meld_s",
     "silicone/oasis",
     "silicone/maptask",
-    "silicone/meld_e",
-    "silicone/meld_s",
     "silicone/dyda_da",
-    "silicone/sem",
-    "silicone/dyda_e",
     "lex_glue/eurlex",
     "lex_glue/scotus",
     "lex_glue/ledgar",
@@ -834,27 +848,27 @@
     "go_emotions/simplified",
     "scicite",
     "liar",
-    "lexical_relation_classification/EVALution",
-    "lexical_relation_classification/BLESS",
     "lexical_relation_classification/CogALexV",
+    "lexical_relation_classification/EVALution",
     "lexical_relation_classification/K&H+N",
+    "lexical_relation_classification/BLESS",
     "lexical_relation_classification/ROOT09",
-    "linguisticprobing/odd_man_out",
-    "linguisticprobing/tree_depth",
-    "linguisticprobing/coordination_inversion",
-    "linguisticprobing/sentence_length",
     "linguisticprobing/obj_number",
-    "linguisticprobing/subj_number",
     "linguisticprobing/bigram_shift",
+    "linguisticprobing/subj_number",
+    "linguisticprobing/sentence_length",
+    "linguisticprobing/odd_man_out",
+    "linguisticprobing/tree_depth",
     "linguisticprobing/top_constituents",
+    "linguisticprobing/coordination_inversion",
     "linguisticprobing/past_present",
-    "crowdflower/political-media-message",
-    "crowdflower/text_emotion",
     "crowdflower/sentiment_nuclear_power",
     "crowdflower/tweet_global_warming",
+    "crowdflower/political-media-message",
+    "crowdflower/text_emotion",
     "crowdflower/corporate-messaging",
-    "crowdflower/airline-sentiment",
     "crowdflower/political-media-audience",
+    "crowdflower/airline-sentiment",
     "crowdflower/political-media-bias",
     "crowdflower/economic-news",
     "ethics/commonsense",
@@ -865,11 +879,6 @@
     "google_wellformed_query",
     "tweets_hate_speech_detection",
     "has_part",
-    "wnut_17/wnut_17",
-    "ncbi_disease/ncbi_disease",
-    "acronym_identification",
-    "jnlpba/jnlpba",
-    "ontonotes_english/SpeedOfMagic--ontonotes_english",
     "blog_authorship_corpus/gender",
     "blog_authorship_corpus/age",
     "blog_authorship_corpus/job",
@@ -883,13 +892,13 @@
     "phrase_similarity",
     "scientific-exaggeration-detection",
     "quarel",
-    "fever-evidence-related/mwong--fever-related",
+    "fever-evidence-related",
     "numer_sense",
     "dynasent/dynabench.dynasent.r1.all/r1",
     "dynasent/dynabench.dynasent.r2.all/r2",
     "Sarcasm_News_Headline",
     "sem_eval_2010_task_8",
-    "auditor_review/demo-org--auditor_review",
+    "auditor_review",
     "medmcqa",
     "Dynasent_Disagreement",
     "Politeness_Disagreement",
@@ -918,12 +927,10 @@
     "synthetic-instruct-gptj-pairwise",
     "scruples",
     "wouldyourather",
-    "attempto-nli",
     "defeasible-nli/atomic",
     "defeasible-nli/snli",
     "help-nli",
     "nli-veridicality-transitivity",
-    "natural-language-satisfiability",
     "lonli",
     "dadc-limit-nli",
     "FLUTE",
@@ -969,10 +976,6 @@
     "oasst2_dense_flat/toxicity",
     "oasst2_dense_flat/helpfulness",
     "mindgames",
-    "universal_dependencies/en_gum/deprel",
-    "universal_dependencies/en_partut/deprel",
-    "universal_dependencies/en_ewt/deprel",
-    "universal_dependencies/en_lines/deprel",
     "ambient",
     "path-naturalness-prediction",
     "civil_comments/toxicity",
@@ -989,21 +992,12 @@
     "Touche23-ValueEval",
     "starcon",
     "banking77",
-    "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",
@@ -1012,13 +1006,9 @@
     "subjectivity",
     "MOH",
     "VUAC",
-    "TroFi",
     "sharc_modified/mod",
     "conceptrules_v2",
     "disrpt/eng.dep.scidtb.rels",
-    "conll2000",
-    "few-nerd/supervised",
-    "finer-139",
     "zero-shot-label-nli",
     "com2sense",
     "scone",
@@ -1037,7 +1027,8 @@
     "esci",
     "chatbot_arena_conversations",
     "dnd_style_intents",
-    "FLD.v2",
+    "FLD.v2/default",
+    "FLD.v2/star",
     "SDOH-NLI",
     "scifact_entailment",
     "feasibilityQA",
@@ -1051,23 +1042,68 @@
     "stepgame",
     "nlgraph",
     "oasst2_pairwise_rlhf_reward",
-    "hh-rlhf/helpful-rejection-sampled",
     "hh-rlhf/helpful-base",
     "hh-rlhf/helpful-online",
+    "hh-rlhf/helpful-rejection-sampled",
     "hh-rlhf/harmless-base",
     "ruletaker",
     "PARARULE-Plus",
     "proofwriter",
     "logical-entailment",
+    "nope",
+    "LogicNLI",
+    "contract-nli/contractnli_a/seg",
+    "contract-nli/contractnli_b/full",
+    "nli4ct_semeval2024",
+    "lsat-ar",
+    "lsat-rc",
+    "biosift-nli",
+    "brainteasers/WP",
+    "brainteasers/SP",
+    "persuasion",
+    "AmbigNQ-clarifying-question",
+    "SIGA-nli",
+    "FOL-nli",
+    "goal-step-wikihow/order",
+    "PARADISE",
+    "doc-nli",
+    "mctest-nli",
+    "patent-phrase-similarity",
+    "natural-language-satisfiability",
+    "idioms-nli",
+    "lifecycle-entailment",
+    "HelpSteer/helpfulness",
+    "HelpSteer/correctness",
+    "HelpSteer/coherence",
+    "HelpSteer/complexity",
+    "HelpSteer/verbosity",
+    "HelpSteer2/helpfulness",
+    "HelpSteer2/correctness",
+    "HelpSteer2/coherence",
+    "HelpSteer2/complexity",
+    "HelpSteer2/verbosity",
+    "MSciNLI",
+    "UltraFeedback-paired",
+    "AES2-essay-scoring",
+    "english-grading/cohesion",
+    "english-grading/syntax",
+    "english-grading/vocabulary",
+    "english-grading/phraseology",
+    "english-grading/grammar",
+    "english-grading/conventions",
+    "wice",
+    "hover",
+    "tasksource_dpo_pairs",
+    "seahorse_summarization_evaluation",
+    "missing-item-prediction/contrastive",
     "babi_nli",
     "gen_debiased_nli",
     "imppres/presupposition",
     "/prag",
-    "blimp-2",
-    "mmlu-4"
+    "blimp-2"
   ],
   "torch_dtype": "float32",
-  "transformers_version": "4.34.1",
+  "transformers_version": "4.42.3",
   "type_vocab_size": 0,
   "vocab_size": 128100
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af30c7ad7235a2054300bc2df1d98149ad6008dd1ef06212be8b32b5d1b3458
+size 567601628