tasksource/deberta-base-long-nli
273.1k
1{2 "_name_or_path": "microsoft/deberta-v3-base",3 "architectures": [4 "DebertaV2ForSequenceClassification"5 ],6 "attention_probs_dropout_prob": 0.1,7 "classifiers_size": [8 3,9 2,10 2,11 2,12 2,13 2,14 1,15 2,16 3,17 2,18 2,19 2,20 3,21 3,22 3,23 3,24 1,25 3,26 3,27 2,28 2,29 3,30 2,31 2,32 6,33 2,34 2,35 2,36 2,37 2,38 2,39 2,40 2,41 3,42 3,43 3,44 3,45 3,46 3,47 3,48 2,49 2,50 2,51 2,52 5,53 3,54 3,55 3,56 3,57 3,58 3,59 3,60 3,61 2,62 2,63 2,64 3,65 3,66 3,67 3,68 3,69 3,70 3,71 2,72 2,73 2,74 2,75 1,76 1,77 1,78 1,79 1,80 1,81 1,82 1,83 1,84 1,85 1,86 1,87 1,88 1,89 1,90 1,91 1,92 1,93 1,94 1,95 1,96 1,97 1,98 1,99 1,100 1,101 1,102 1,103 1,104 1,105 1,106 1,107 1,108 1,109 1,110 1,111 1,112 1,113 1,114 1,115 1,116 1,117 1,118 1,119 1,120 1,121 1,122 1,123 1,124 1,125 1,126 1,127 1,128 1,129 1,130 1,131 1,132 1,133 1,134 1,135 1,136 1,137 1,138 1,139 1,140 1,141 1,142 1,143 1,144 1,145 1,146 1,147 1,148 1,149 1,150 1,151 1,152 1,153 1,154 1,155 1,156 1,157 1,158 1,159 1,160 1,161 1,162 1,163 1,164 1,165 1,166 1,167 1,168 1,169 1,170 1,171 1,172 1,173 1,174 1,175 1,176 1,177 1,178 1,179 1,180 1,181 1,182 1,183 1,184 1,185 1,186 1,187 1,188 1,189 1,190 1,191 1,192 1,193 1,194 1,195 1,196 1,197 1,198 1,199 1,200 1,201 1,202 1,203 2,204 2,205 2,206 2,207 2,208 2,209 20,210 50,211 3,212 3,213 4,214 2,215 8,216 20,217 2,218 4,219 2,220 2,221 3,222 3,223 3,224 3,225 3,226 3,227 174,228 2,229 41,230 3,231 51,232 2,233 2,234 2,235 2,236 2,237 2,238 16,239 3,240 2,241 8,242 2,243 2,244 18,245 2,246 17,247 3,248 3,249 7,250 11,251 12,252 7,253 4,254 42,255 3,256 100,257 13,258 100,259 8,260 1,261 20,262 2,263 2,264 4,265 5,266 3,267 4,268 14,269 2,270 6,271 4,272 2,273 1,274 3,275 10,276 3,277 10,278 4,279 2,280 7,281 6,282 28,283 3,284 6,285 7,286 3,287 4,288 5,289 6,290 2,291 2,292 2,293 6,294 20,295 7,296 2,297 2,298 2,299 9,300 13,301 2,302 3,303 4,304 3,305 2,306 4,307 2,308 2,309 2,310 2,311 2,312 4,313 1,314 2,315 1,316 2,317 49,318 40,319 10,320 4,321 1,322 2,323 2,324 1,325 5,326 2,327 3,328 2,329 2,330 12,331 3,332 3,333 2,334 19,335 3,336 1,337 2,338 2,339 2,340 2,341 2,342 1,343 2,344 2,345 1,346 1,347 2,348 3,349 2,350 1,351 4,352 3,353 1,354 1,355 1,356 2,357 3,358 2,359 3,360 1,361 1,362 2,363 1,364 2,365 2,366 2,367 2,368 3,369 2,370 2,371 2,372 1,373 3,374 2,375 2,376 1,377 1,378 1,379 1,380 2,381 1,382 1,383 1,384 1,385 4,386 1,387 1,388 1,389 1,390 3,391 1,392 3,393 1,394 2,395 2,396 1,397 2,398 3,399 3,400 2,401 1,402 3,403 1,404 1,405 3,406 1,407 3,408 2,409 1,410 1,411 1,412 2,413 2,414 1,415 1,416 1,417 1,418 1,419 1,420 1,421 1,422 1,423 1,424 2,425 2,426 2,427 2,428 77,429 3,430 2,431 2,432 1,433 1,434 2,435 3,436 18,437 13,438 2,439 2,440 2,441 2,442 2,443 4,444 2,445 24,446 3,447 2,448 2,449 1,450 2,451 2,452 3,453 1,454 2,455 3,456 2,457 3,458 3,459 2,460 2,461 4,462 1,463 17,464 3,465 3,466 2,467 3,468 2,469 3,470 3,471 2,472 1,473 1,474 3,475 2,476 9,477 2,478 1,479 1,480 1,481 1,482 1,483 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 3,534 3,535 3,536 1537 ],538 "hidden_act": "gelu",539 "hidden_dropout_prob": 0.1,540 "hidden_size": 768,541 "id2label": {542 "0": "entailment",543 "1": "neutral",544 "2": "contradiction"545 },546 "initializer_range": 0.02,547 "intermediate_size": 3072,548 "label2id": {549 "contradiction": 2,550 "entailment": 0,551 "neutral": 1552 },553 "layer_norm_eps": 1e-07,554 "max_position_embeddings": 1280,555 "max_relative_positions": -1,556 "model_type": "deberta-v2",557 "norm_rel_ebd": "layer_norm",558 "num_attention_heads": 12,559 "num_hidden_layers": 12,560 "pad_token_id": 0,561 "pooler_dropout": 0,562 "pooler_hidden_act": "gelu",563 "pooler_hidden_size": 768,564 "pos_att_type": [565 "p2c",566 "c2p"567 ],568 "position_biased_input": false,569 "position_buckets": 256,570 "relative_attention": true,571 "share_att_key": true,572 "tasks": [573 "glue/mnli",574 "glue/qnli",575 "glue/rte",576 "glue/wnli",577 "glue/mrpc",578 "glue/qqp",579 "glue/stsb",580 "super_glue/boolq",581 "super_glue/cb",582 "super_glue/multirc",583 "super_glue/wic",584 "super_glue/axg",585 "anli/a1",586 "anli/a2",587 "anli/a3",588 "sick/label",589 "sick/relatedness",590 "sick/entailment_AB",591 "snli",592 "scitail/snli_format",593 "hans",594 "WANLI",595 "recast/recast_puns",596 "recast/recast_factuality",597 "recast/recast_kg_relations",598 "recast/recast_verbnet",599 "recast/recast_verbcorner",600 "recast/recast_ner",601 "recast/recast_megaveridicality",602 "recast/recast_sentiment",603 "probability_words_nli/reasoning_1hop",604 "probability_words_nli/usnli",605 "probability_words_nli/reasoning_2hop",606 "nan-nli",607 "nli_fever",608 "breaking_nli",609 "conj_nli",610 "fracas",611 "dialogue_nli",612 "mpe",613 "dnc",614 "recast_white/fnplus",615 "recast_white/sprl",616 "recast_white/dpr",617 "joci",618 "robust_nli/IS_CS",619 "robust_nli/LI_LI",620 "robust_nli/ST_WO",621 "robust_nli/PI_SP",622 "robust_nli/PI_CD",623 "robust_nli/ST_SE",624 "robust_nli/ST_NE",625 "robust_nli/ST_LM",626 "robust_nli_is_sd",627 "robust_nli_li_ts",628 "add_one_rte",629 "imppres/implicature_gradable_adjective/log",630 "imppres/implicature_modals/log",631 "imppres/implicature_numerals_10_100/log",632 "imppres/implicature_quantifiers/log",633 "imppres/implicature_connectives/log",634 "imppres/implicature_gradable_verb/log",635 "imppres/implicature_numerals_2_3/log",636 "hlgd",637 "paws/labeled_final",638 "paws/labeled_swap",639 "medical_questions_pairs",640 "model-written-evals",641 "truthful_qa/multiple_choice",642 "fig-qa",643 "bigbench/discourse_marker_prediction",644 "bigbench/gre_reading_comprehension",645 "bigbench/simple_ethical_questions",646 "bigbench/known_unknowns",647 "bigbench/fact_checker",648 "bigbench/phrase_relatedness",649 "bigbench/irony_identification",650 "bigbench/crash_blossom",651 "bigbench/physical_intuition",652 "bigbench/analytic_entailment",653 "bigbench/play_dialog_same_or_different",654 "bigbench/metaphor_boolean",655 "bigbench/undo_permutation",656 "bigbench/disambiguation_qa",657 "bigbench/metaphor_understanding",658 "bigbench/nonsense_words_grammar",659 "bigbench/logical_deduction",660 "bigbench/sentence_ambiguity",661 "bigbench/key_value_maps",662 "bigbench/checkmate_in_one",663 "bigbench/code_line_description",664 "bigbench/crass_ai",665 "bigbench/movie_dialog_same_or_different",666 "bigbench/strategyqa",667 "bigbench/hhh_alignment",668 "bigbench/english_proverbs",669 "bigbench/cs_algorithms",670 "bigbench/formal_fallacies_syllogisms_negation",671 "bigbench/conceptual_combinations",672 "bigbench/geometric_shapes",673 "bigbench/tracking_shuffled_objects",674 "bigbench/arithmetic",675 "bigbench/misconceptions",676 "bigbench/odd_one_out",677 "bigbench/international_phonetic_alphabet_nli",678 "bigbench/social_iqa",679 "bigbench/logical_fallacy_detection",680 "bigbench/hyperbaton",681 "bigbench/novel_concepts",682 "bigbench/similarities_abstraction",683 "bigbench/timedial",684 "bigbench/salient_translation_error_detection",685 "bigbench/cifar10_classification",686 "bigbench/winowhy",687 "bigbench/mathematical_induction",688 "bigbench/real_or_fake_text",689 "bigbench/epistemic_reasoning",690 "bigbench/riddle_sense",691 "bigbench/identify_odd_metaphor",692 "bigbench/human_organs_senses",693 "bigbench/emojis_emotion_prediction",694 "bigbench/logical_args",695 "bigbench/anachronisms",696 "bigbench/bbq_lite_json",697 "bigbench/general_knowledge",698 "bigbench/logical_sequence",699 "bigbench/navigate",700 "bigbench/analogical_similarity",701 "bigbench/authorship_verification",702 "bigbench/elementary_math_qa",703 "bigbench/goal_step_wikihow",704 "bigbench/empirical_judgments",705 "bigbench/question_selection",706 "bigbench/temporal_sequences",707 "bigbench/mnist_ascii",708 "bigbench/color",709 "bigbench/date_understanding",710 "bigbench/figure_of_speech_detection",711 "bigbench/contextual_parametric_knowledge_conflicts",712 "bigbench/ruin_names",713 "bigbench/abstract_narrative_understanding",714 "bigbench/physics",715 "bigbench/understanding_fables",716 "bigbench/identify_math_theorems",717 "bigbench/penguins_in_a_table",718 "bigbench/vitaminc_fact_verification",719 "bigbench/social_support",720 "bigbench/strange_stories",721 "bigbench/dark_humor_detection",722 "bigbench/fantasy_reasoning",723 "bigbench/logic_grid_puzzle",724 "bigbench/emoji_movie",725 "bigbench/moral_permissibility",726 "bigbench/symbol_interpretation",727 "bigbench/presuppositions_as_nli",728 "bigbench/dyck_languages",729 "bigbench/implicatures",730 "bigbench/suicide_risk",731 "bigbench/unit_interpretation",732 "bigbench/intent_recognition",733 "bigbench/movie_recommendation",734 "bigbench/snarks",735 "bigbench/evaluating_information_essentiality",736 "bigbench/sports_understanding",737 "bigbench/entailed_polarity",738 "bigbench/causal_judgment",739 "bigbench/cause_and_effect",740 "bigbench/implicit_relations",741 "bigbench/reasoning_about_colored_objects",742 "bigbench/hindu_knowledge",743 "cos_e/v1.0",744 "cosmos_qa",745 "dream",746 "openbookqa",747 "qasc",748 "quartz",749 "quail",750 "head_qa/en",751 "sciq",752 "social_i_qa",753 "wiki_hop/original",754 "wiqa",755 "piqa",756 "hellaswag",757 "super_glue/copa",758 "balanced-copa",759 "e-CARE",760 "art",761 "winogrande/winogrande_xl",762 "codah/codah",763 "ai2_arc/ARC-Easy/challenge",764 "ai2_arc/ARC-Challenge/challenge",765 "definite_pronoun_resolution",766 "swag/regular",767 "math_qa",768 "glue/cola",769 "glue/sst2",770 "utilitarianism",771 "amazon_counterfactual/en",772 "insincere-questions",773 "toxic_conversations",774 "TuringBench",775 "trec",776 "vitaminc",777 "hope_edi/english",778 "rumoureval_2019/RumourEval2019",779 "ethos/binary",780 "ethos/multilabel",781 "tweet_eval/emoji",782 "tweet_eval/offensive",783 "tweet_eval/emotion",784 "tweet_eval/hate",785 "tweet_eval/irony",786 "tweet_eval/sentiment",787 "tweet_eval/stance_abortion",788 "tweet_eval/stance_atheism",789 "tweet_eval/stance_climate",790 "tweet_eval/stance_feminist",791 "tweet_eval/stance_hillary",792 "discovery/discovery",793 "pragmeval/squinky-formality",794 "pragmeval/switchboard",795 "pragmeval/verifiability",796 "pragmeval/mrda",797 "pragmeval/squinky-informativeness",798 "pragmeval/squinky-implicature",799 "pragmeval/emobank-arousal",800 "pragmeval/emobank-dominance",801 "pragmeval/emobank-valence",802 "pragmeval/sarcasm",803 "pragmeval/pdtb",804 "pragmeval/persuasiveness-claimtype",805 "pragmeval/persuasiveness-relevance",806 "pragmeval/persuasiveness-premisetype",807 "pragmeval/persuasiveness-eloquence",808 "pragmeval/persuasiveness-strength",809 "pragmeval/stac",810 "pragmeval/persuasiveness-specificity",811 "pragmeval/gum",812 "pragmeval/emergent",813 "silicone/sem",814 "silicone/meld_e",815 "silicone/iemocap",816 "silicone/maptask",817 "silicone/dyda_e",818 "silicone/dyda_da",819 "silicone/oasis",820 "silicone/meld_s",821 "lex_glue/eurlex",822 "lex_glue/scotus",823 "lex_glue/ledgar",824 "lex_glue/unfair_tos",825 "lex_glue/case_hold",826 "language-identification",827 "imdb",828 "rotten_tomatoes",829 "ag_news",830 "yelp_review_full/yelp_review_full",831 "financial_phrasebank/sentences_allagree",832 "poem_sentiment",833 "dbpedia_14/dbpedia_14",834 "amazon_polarity/amazon_polarity",835 "app_reviews",836 "hate_speech18",837 "sms_spam",838 "humicroedit/subtask-1",839 "humicroedit/subtask-2",840 "snips_built_in_intents",841 "hate_speech_offensive",842 "yahoo_answers_topics",843 "stackoverflow-questions",844 "hyperpartisan_news",845 "sciie",846 "citation_intent",847 "go_emotions/simplified",848 "scicite",849 "liar",850 "lexical_relation_classification/EVALution",851 "lexical_relation_classification/ROOT09",852 "lexical_relation_classification/K&H+N",853 "lexical_relation_classification/CogALexV",854 "lexical_relation_classification/BLESS",855 "linguisticprobing/subj_number",856 "linguisticprobing/past_present",857 "linguisticprobing/obj_number",858 "linguisticprobing/sentence_length",859 "linguisticprobing/top_constituents",860 "linguisticprobing/tree_depth",861 "linguisticprobing/coordination_inversion",862 "linguisticprobing/odd_man_out",863 "linguisticprobing/bigram_shift",864 "crowdflower/political-media-message",865 "crowdflower/text_emotion",866 "crowdflower/political-media-audience",867 "crowdflower/economic-news",868 "crowdflower/corporate-messaging",869 "crowdflower/airline-sentiment",870 "crowdflower/tweet_global_warming",871 "crowdflower/sentiment_nuclear_power",872 "crowdflower/political-media-bias",873 "ethics/commonsense",874 "ethics/deontology",875 "ethics/justice",876 "ethics/virtue",877 "emo/emo2019",878 "google_wellformed_query",879 "tweets_hate_speech_detection",880 "has_part",881 "blog_authorship_corpus/gender",882 "blog_authorship_corpus/age",883 "blog_authorship_corpus/job",884 "open_question_type",885 "health_fact",886 "commonsense_qa",887 "mc_taco",888 "ade_corpus_v2/Ade_corpus_v2_classification",889 "discosense",890 "circa",891 "phrase_similarity",892 "scientific-exaggeration-detection",893 "quarel",894 "fever-evidence-related",895 "numer_sense",896 "dynasent/dynabench.dynasent.r1.all/r1",897 "dynasent/dynabench.dynasent.r2.all/r2",898 "Sarcasm_News_Headline",899 "sem_eval_2010_task_8",900 "auditor_review",901 "medmcqa",902 "Dynasent_Disagreement",903 "Politeness_Disagreement",904 "SBIC_Disagreement",905 "SChem_Disagreement",906 "Dilemmas_Disagreement",907 "logiqa",908 "wiki_qa",909 "cycic_classification",910 "cycic_multiplechoice",911 "sts-companion",912 "commonsense_qa_2.0",913 "lingnli",914 "monotonicity-entailment",915 "arct",916 "scinli",917 "naturallogic",918 "onestop_qa",919 "moral_stories/full",920 "prost",921 "dynahate",922 "syntactic-augmentation-nli",923 "autotnli",924 "CONDAQA",925 "webgpt_comparisons",926 "synthetic-instruct-gptj-pairwise",927 "scruples",928 "wouldyourather",929 "defeasible-nli/atomic",930 "defeasible-nli/snli",931 "help-nli",932 "nli-veridicality-transitivity",933 "lonli",934 "dadc-limit-nli",935 "FLUTE",936 "strategy-qa",937 "summarize_from_feedback/comparisons",938 "folio",939 "tomi-nli",940 "avicenna",941 "SHP",942 "MedQA-USMLE-4-options-hf",943 "wikimedqa/medwiki",944 "cicero",945 "CREAK",946 "mutual",947 "NeQA",948 "quote-repetition",949 "redefine-math",950 "puzzte",951 "implicatures",952 "race/high",953 "race/middle",954 "race-c",955 "spartqa-yn",956 "spartqa-mchoice",957 "temporal-nli",958 "riddle_sense",959 "clcd-english",960 "twentyquestions",961 "reclor",962 "counterfactually-augmented-imdb",963 "counterfactually-augmented-snli",964 "cnli",965 "boolq-natural-perturbations",966 "acceptability-prediction",967 "equate",968 "ScienceQA_text_only",969 "ekar_english",970 "implicit-hate-stg1",971 "chaos-mnli-ambiguity",972 "headline_cause/en_simple",973 "logiqa-2.0-nli",974 "oasst2_dense_flat/quality",975 "oasst2_dense_flat/toxicity",976 "oasst2_dense_flat/helpfulness",977 "mindgames",978 "ambient",979 "path-naturalness-prediction",980 "civil_comments/toxicity",981 "civil_comments/severe_toxicity",982 "civil_comments/obscene",983 "civil_comments/threat",984 "civil_comments/insult",985 "civil_comments/identity_attack",986 "civil_comments/sexual_explicit",987 "cloth",988 "dgen",989 "I2D2",990 "args_me",991 "Touche23-ValueEval",992 "starcon",993 "banking77",994 "ConTRoL-nli",995 "tracie",996 "sherliic",997 "sen-making/1",998 "sen-making/2",999 "winowhy",1000 "robustLR",1001 "v1/gen_train234_test2to10",1002 "logical-fallacy",1003 "parade",1004 "cladder",1005 "subjectivity",1006 "MOH",1007 "VUAC",1008 "sharc_modified/mod",1009 "conceptrules_v2",1010 "disrpt/eng.dep.scidtb.rels",1011 "zero-shot-label-nli",1012 "com2sense",1013 "scone",1014 "winodict",1015 "fool-me-twice",1016 "monli",1017 "corr2cause",1018 "lsat_qa/all",1019 "apt",1020 "twitter-financial-news-sentiment",1021 "icl-symbol-tuning-instruct",1022 "SpaceNLI",1023 "propsegment/nli",1024 "HatemojiBuild",1025 "regset",1026 "esci",1027 "chatbot_arena_conversations",1028 "dnd_style_intents",1029 "FLD.v2/default",1030 "FLD.v2/star",1031 "SDOH-NLI",1032 "scifact_entailment",1033 "feasibilityQA",1034 "simple_pair",1035 "AdjectiveScaleProbe-nli",1036 "resnli",1037 "SpaRTUN",1038 "ReSQ",1039 "semantic_fragments_nli",1040 "dataset_train_nli",1041 "stepgame",1042 "nlgraph",1043 "oasst2_pairwise_rlhf_reward",1044 "hh-rlhf/helpful-online",1045 "hh-rlhf/helpful-rejection-sampled",1046 "hh-rlhf/helpful-base",1047 "hh-rlhf/harmless-base",1048 "ruletaker",1049 "PARARULE-Plus",1050 "proofwriter",1051 "logical-entailment",1052 "nope",1053 "LogicNLI",1054 "contract-nli/contractnli_a/seg",1055 "contract-nli/contractnli_b/full",1056 "nli4ct_semeval2024",1057 "lsat-ar",1058 "lsat-rc",1059 "biosift-nli",1060 "brainteasers/SP",1061 "brainteasers/WP",1062 "persuasion",1063 "AmbigNQ-clarifying-question",1064 "SIGA-nli",1065 "FOL-nli",1066 "goal-step-wikihow/order",1067 "PARADISE",1068 "doc-nli",1069 "mctest-nli",1070 "patent-phrase-similarity",1071 "natural-language-satisfiability",1072 "idioms-nli",1073 "lifecycle-entailment",1074 "HelpSteer/helpfulness",1075 "HelpSteer/correctness",1076 "HelpSteer/coherence",1077 "HelpSteer/complexity",1078 "HelpSteer/verbosity",1079 "HelpSteer2/helpfulness",1080 "HelpSteer2/correctness",1081 "HelpSteer2/coherence",1082 "HelpSteer2/complexity",1083 "HelpSteer2/verbosity",1084 "MSciNLI",1085 "UltraFeedback-paired",1086 "AES2-essay-scoring",1087 "english-grading/cohesion",1088 "english-grading/syntax",1089 "english-grading/vocabulary",1090 "english-grading/phraseology",1091 "english-grading/grammar",1092 "english-grading/conventions",1093 "wice",1094 "hover",1095 "tasksource_dpo_pairs",1096 "seahorse_summarization_evaluation",1097 "babi_nli",1098 "gen_debiased_nli",1099 "imppres/presupposition",1100 "/prag",1101 "blimp-2"1102 ],1103 "torch_dtype": "float32",1104 "transformers_version": "4.42.3",1105 "type_vocab_size": 0,1106 "vocab_size": 1281001107}1108