Upload DebertaV2ForSequenceClassification

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "sileod/deberta-v3-base-tasksource-nli",
+  "_name_or_path": "microsoft/deberta-v3-base",
   "architectures": [
     "DebertaV2ForSequenceClassification"
   ],
@@ -27,13 +27,13 @@
     2,
     2,
     3,
+    6,
     2,
     2,
     2,
     2,
     2,
     2,
-    6,
     2,
     2,
     2,
@@ -213,46 +213,46 @@
     4,
     2,
     8,
-    20,
     2,
     2,
-    4,
     2,
+    4,
     3,
+    20,
     3,
     3,
     3,
     3,
     3,
     174,
-    2,
-    3,
-    51,
     41,
+    51,
     2,
+    3,
     2,
     2,
     2,
     2,
     2,
-    2,
-    18,
     3,
     16,
     17,
-    3,
     2,
     8,
     2,
-    2,
     3,
+    2,
+    2,
+    18,
+    2,
     3,
-    42,
-    4,
     7,
-    11,
     12,
+    4,
     7,
+    42,
+    3,
+    11,
     100,
     13,
     100,
@@ -283,27 +283,27 @@
     3,
     6,
     6,
-    7,
     5,
+    7,
     4,
     3,
-    7,
+    6,
     20,
     2,
+    7,
     2,
     2,
     2,
     2,
-    6,
     2,
-    9,
-    4,
+    3,
     2,
-    4,
     13,
-    3,
-    3,
     2,
+    4,
+    9,
+    4,
+    3,
     2,
     2,
     2,
@@ -528,6 +528,8 @@
     6,
     3,
     2,
+    1,
+    2,
     3,
     3,
     3,
@@ -549,7 +551,7 @@
     "neutral": 1
   },
   "layer_norm_eps": 1e-07,
-  "max_position_embeddings": 1024,
+  "max_position_embeddings": 1280,
   "max_relative_positions": -1,
   "model_type": "deberta-v2",
   "norm_rel_ebd": "layer_norm",
@@ -590,14 +592,14 @@
     "scitail/snli_format",
     "hans",
     "WANLI",
+    "recast/recast_kg_relations",
     "recast/recast_sentiment",
-    "recast/recast_ner",
-    "recast/recast_verbcorner",
+    "recast/recast_puns",
     "recast/recast_verbnet",
+    "recast/recast_verbcorner",
     "recast/recast_factuality",
-    "recast/recast_puns",
-    "recast/recast_kg_relations",
     "recast/recast_megaveridicality",
+    "recast/recast_ner",
     "probability_words_nli/reasoning_1hop",
     "probability_words_nli/reasoning_2hop",
     "probability_words_nli/usnli",
@@ -624,13 +626,13 @@
     "robust_nli_is_sd",
     "robust_nli_li_ts",
     "add_one_rte",
-    "imppres/implicature_connectives/log",
-    "imppres/implicature_gradable_adjective/log",
-    "imppres/implicature_quantifiers/log",
     "imppres/implicature_numerals_10_100/log",
     "imppres/implicature_modals/log",
     "imppres/implicature_gradable_verb/log",
+    "imppres/implicature_connectives/log",
+    "imppres/implicature_gradable_adjective/log",
     "imppres/implicature_numerals_2_3/log",
+    "imppres/implicature_quantifiers/log",
     "hlgd",
     "paws/labeled_final",
     "paws/labeled_swap",
@@ -638,106 +640,106 @@
     "model-written-evals",
     "truthful_qa/multiple_choice",
     "fig-qa",
-    "bigbench/general_knowledge",
-    "bigbench/physical_intuition",
-    "bigbench/bbq_lite_json",
-    "bigbench/elementary_math_qa",
-    "bigbench/human_organs_senses",
+    "bigbench/known_unknowns",
+    "bigbench/formal_fallacies_syllogisms_negation",
+    "bigbench/presuppositions_as_nli",
+    "bigbench/metaphor_understanding",
+    "bigbench/cause_and_effect",
+    "bigbench/simple_ethical_questions",
+    "bigbench/color",
+    "bigbench/similarities_abstraction",
     "bigbench/misconceptions",
+    "bigbench/english_proverbs",
+    "bigbench/sports_understanding",
+    "bigbench/metaphor_boolean",
+    "bigbench/logical_fallacy_detection",
+    "bigbench/logic_grid_puzzle",
+    "bigbench/empirical_judgments",
+    "bigbench/mnist_ascii",
+    "bigbench/entailed_polarity",
+    "bigbench/elementary_math_qa",
+    "bigbench/gre_reading_comprehension",
     "bigbench/social_iqa",
-    "bigbench/causal_judgment",
+    "bigbench/figure_of_speech_detection",
+    "bigbench/timedial",
+    "bigbench/moral_permissibility",
+    "bigbench/evaluating_information_essentiality",
+    "bigbench/implicit_relations",
+    "bigbench/real_or_fake_text",
+    "bigbench/hyperbaton",
+    "bigbench/odd_one_out",
+    "bigbench/play_dialog_same_or_different",
+    "bigbench/vitaminc_fact_verification",
+    "bigbench/goal_step_wikihow",
+    "bigbench/unit_interpretation",
     "bigbench/physics",
-    "bigbench/identify_math_theorems",
-    "bigbench/fact_checker",
-    "bigbench/empirical_judgments",
+    "bigbench/code_line_description",
+    "bigbench/phrase_relatedness",
+    "bigbench/general_knowledge",
+    "bigbench/identify_odd_metaphor",
     "bigbench/key_value_maps",
-    "bigbench/hhh_alignment",
-    "bigbench/logical_deduction",
-    "bigbench/similarities_abstraction",
-    "bigbench/color",
-    "bigbench/evaluating_information_essentiality",
-    "bigbench/temporal_sequences",
-    "bigbench/authorship_verification",
-    "bigbench/conceptual_combinations",
-    "bigbench/gre_reading_comprehension",
-    "bigbench/symbol_interpretation",
+    "bigbench/sentence_ambiguity",
+    "bigbench/disambiguation_qa",
+    "bigbench/movie_dialog_same_or_different",
+    "bigbench/discourse_marker_prediction",
+    "bigbench/social_support",
+    "bigbench/anachronisms",
     "bigbench/undo_permutation",
-    "bigbench/snarks",
-    "bigbench/mnist_ascii",
-    "bigbench/arithmetic",
+    "bigbench/irony_identification",
     "bigbench/nonsense_words_grammar",
     "bigbench/logical_sequence",
+    "bigbench/reasoning_about_colored_objects",
+    "bigbench/causal_judgment",
+    "bigbench/geometric_shapes",
+    "bigbench/logical_deduction",
+    "bigbench/question_selection",
+    "bigbench/hhh_alignment",
+    "bigbench/analytic_entailment",
+    "bigbench/riddle_sense",
     "bigbench/movie_recommendation",
-    "bigbench/cs_algorithms",
-    "bigbench/anachronisms",
-    "bigbench/known_unknowns",
+    "bigbench/penguins_in_a_table",
     "bigbench/intent_recognition",
-    "bigbench/entailed_polarity",
-    "bigbench/tracking_shuffled_objects",
+    "bigbench/conceptual_combinations",
+    "bigbench/cs_algorithms",
+    "bigbench/temporal_sequences",
     "bigbench/salient_translation_error_detection",
+    "bigbench/abstract_narrative_understanding",
+    "bigbench/authorship_verification",
+    "bigbench/winowhy",
+    "bigbench/strategyqa",
     "bigbench/implicatures",
-    "bigbench/international_phonetic_alphabet_nli",
-    "bigbench/mathematical_induction",
-    "bigbench/irony_identification",
-    "bigbench/movie_dialog_same_or_different",
-    "bigbench/moral_permissibility",
-    "bigbench/goal_step_wikihow",
-    "bigbench/fantasy_reasoning",
-    "bigbench/timedial",
-    "bigbench/figure_of_speech_detection",
+    "bigbench/snarks",
+    "bigbench/human_organs_senses",
+    "bigbench/arithmetic",
+    "bigbench/tracking_shuffled_objects",
+    "bigbench/date_understanding",
+    "bigbench/understanding_fables",
     "bigbench/checkmate_in_one",
-    "bigbench/winowhy",
-    "bigbench/dyck_languages",
-    "bigbench/social_support",
-    "bigbench/unit_interpretation",
-    "bigbench/english_proverbs",
+    "bigbench/cifar10_classification",
+    "bigbench/navigate",
     "bigbench/ruin_names",
-    "bigbench/crash_blossom",
+    "bigbench/bbq_lite_json",
+    "bigbench/suicide_risk",
+    "bigbench/dyck_languages",
+    "bigbench/emoji_movie",
+    "bigbench/contextual_parametric_knowledge_conflicts",
+    "bigbench/novel_concepts",
+    "bigbench/fantasy_reasoning",
+    "bigbench/mathematical_induction",
     "bigbench/emojis_emotion_prediction",
-    "bigbench/understanding_fables",
-    "bigbench/implicit_relations",
-    "bigbench/cifar10_classification",
-    "bigbench/analytic_entailment",
-    "bigbench/vitaminc_fact_verification",
-    "bigbench/phrase_relatedness",
-    "bigbench/epistemic_reasoning",
-    "bigbench/penguins_in_a_table",
-    "bigbench/question_selection",
-    "bigbench/reasoning_about_colored_objects",
-    "bigbench/strategyqa",
+    "bigbench/symbol_interpretation",
+    "bigbench/strange_stories",
+    "bigbench/identify_math_theorems",
     "bigbench/dark_humor_detection",
-    "bigbench/formal_fallacies_syllogisms_negation",
-    "bigbench/odd_one_out",
-    "bigbench/novel_concepts",
-    "bigbench/hyperbaton",
-    "bigbench/suicide_risk",
-    "bigbench/navigate",
     "bigbench/crass_ai",
-    "bigbench/hindu_knowledge",
-    "bigbench/disambiguation_qa",
-    "bigbench/riddle_sense",
-    "bigbench/presuppositions_as_nli",
-    "bigbench/strange_stories",
-    "bigbench/emoji_movie",
-    "bigbench/metaphor_understanding",
+    "bigbench/international_phonetic_alphabet_nli",
     "bigbench/logical_args",
-    "bigbench/identify_odd_metaphor",
-    "bigbench/logical_fallacy_detection",
-    "bigbench/code_line_description",
-    "bigbench/geometric_shapes",
-    "bigbench/discourse_marker_prediction",
-    "bigbench/sentence_ambiguity",
-    "bigbench/abstract_narrative_understanding",
+    "bigbench/epistemic_reasoning",
+    "bigbench/hindu_knowledge",
+    "bigbench/physical_intuition",
+    "bigbench/crash_blossom",
     "bigbench/analogical_similarity",
-    "bigbench/cause_and_effect",
-    "bigbench/simple_ethical_questions",
-    "bigbench/sports_understanding",
-    "bigbench/date_understanding",
-    "bigbench/metaphor_boolean",
-    "bigbench/logic_grid_puzzle",
-    "bigbench/contextual_parametric_knowledge_conflicts",
-    "bigbench/real_or_fake_text",
-    "bigbench/play_dialog_same_or_different",
+    "bigbench/fact_checker",
     "cos_e/v1.0",
     "cosmos_qa",
     "dream",
@@ -776,46 +778,46 @@
     "rumoureval_2019/RumourEval2019",
     "ethos/binary",
     "ethos/multilabel",
-    "tweet_eval/emoji",
-    "tweet_eval/hate",
+    "tweet_eval/irony",
     "tweet_eval/offensive",
+    "tweet_eval/hate",
     "tweet_eval/emotion",
-    "tweet_eval/irony",
     "tweet_eval/sentiment",
+    "tweet_eval/emoji",
     "tweet_eval/stance_abortion",
     "tweet_eval/stance_atheism",
     "tweet_eval/stance_climate",
     "tweet_eval/stance_feminist",
     "tweet_eval/stance_hillary",
     "discovery/discovery",
+    "pragmeval/switchboard",
+    "pragmeval/mrda",
     "pragmeval/squinky-informativeness",
     "pragmeval/verifiability",
-    "pragmeval/mrda",
-    "pragmeval/switchboard",
-    "pragmeval/emobank-arousal",
+    "pragmeval/squinky-implicature",
+    "pragmeval/squinky-formality",
     "pragmeval/emobank-valence",
     "pragmeval/emobank-dominance",
-    "pragmeval/squinky-formality",
-    "pragmeval/squinky-implicature",
-    "pragmeval/sarcasm",
-    "pragmeval/persuasiveness-specificity",
-    "pragmeval/stac",
+    "pragmeval/emobank-arousal",
     "pragmeval/emergent",
     "pragmeval/pdtb",
     "pragmeval/gum",
-    "pragmeval/persuasiveness-claimtype",
-    "pragmeval/persuasiveness-strength",
+    "pragmeval/persuasiveness-eloquence",
     "pragmeval/persuasiveness-premisetype",
     "pragmeval/persuasiveness-relevance",
-    "pragmeval/persuasiveness-eloquence",
+    "pragmeval/persuasiveness-claimtype",
+    "pragmeval/sarcasm",
+    "pragmeval/persuasiveness-strength",
+    "pragmeval/stac",
+    "pragmeval/persuasiveness-specificity",
     "silicone/sem",
-    "silicone/meld_s",
-    "silicone/oasis",
+    "silicone/meld_e",
+    "silicone/maptask",
     "silicone/dyda_da",
     "silicone/dyda_e",
+    "silicone/oasis",
+    "silicone/meld_s",
     "silicone/iemocap",
-    "silicone/maptask",
-    "silicone/meld_e",
     "lex_glue/eurlex",
     "lex_glue/scotus",
     "lex_glue/ledgar",
@@ -846,28 +848,28 @@
     "scicite",
     "liar",
     "lexical_relation_classification/BLESS",
-    "lexical_relation_classification/EVALution",
     "lexical_relation_classification/CogALexV",
+    "lexical_relation_classification/EVALution",
     "lexical_relation_classification/K&H+N",
     "lexical_relation_classification/ROOT09",
-    "linguisticprobing/tree_depth",
+    "linguisticprobing/sentence_length",
     "linguisticprobing/top_constituents",
+    "linguisticprobing/coordination_inversion",
+    "linguisticprobing/tree_depth",
     "linguisticprobing/subj_number",
+    "linguisticprobing/obj_number",
+    "linguisticprobing/past_present",
     "linguisticprobing/bigram_shift",
     "linguisticprobing/odd_man_out",
-    "linguisticprobing/coordination_inversion",
-    "linguisticprobing/past_present",
-    "linguisticprobing/sentence_length",
-    "linguisticprobing/obj_number",
-    "crowdflower/political-media-message",
-    "crowdflower/corporate-messaging",
-    "crowdflower/tweet_global_warming",
-    "crowdflower/sentiment_nuclear_power",
-    "crowdflower/text_emotion",
-    "crowdflower/airline-sentiment",
     "crowdflower/economic-news",
     "crowdflower/political-media-bias",
+    "crowdflower/text_emotion",
     "crowdflower/political-media-audience",
+    "crowdflower/sentiment_nuclear_power",
+    "crowdflower/political-media-message",
+    "crowdflower/corporate-messaging",
+    "crowdflower/airline-sentiment",
+    "crowdflower/tweet_global_warming",
     "ethics/commonsense",
     "ethics/deontology",
     "ethics/justice",
@@ -1090,6 +1092,8 @@
     "english-grading/grammar",
     "english-grading/conventions",
     "wice",
+    "hover",
+    "tasksource_dpo_pairs",
     "babi_nli",
     "gen_debiased_nli",
     "imppres/presupposition",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00dfda6b5886f4aca861bc5234850d74358a3e8dcbe78c3d55038dded6fd5c17
+oid sha256:9ae1e040afa694928b43261010315a2ccbe630744935c65fba2eb308d2daa26e
 size 737722356