Upload folder using huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "sileod/deberta-v3-large-tasksource-nli",
+  "_name_or_path": "sileod/deberta-v3-base-tasksource-nli",
   "architectures": [
     "DebertaV2ForSequenceClassification"
   ],
@@ -28,9 +28,9 @@
     2,
     3,
     2,
+    6,
     2,
     2,
-    6,
     2,
     2,
     2,
@@ -204,6 +204,7 @@
     1,
     1,
     1,
+    1,
     2,
     2,
     2,
@@ -219,10 +220,10 @@
     8,
     3,
     2,
-    20,
-    4,
     2,
     2,
+    4,
+    20,
     3,
     3,
     3,
@@ -230,33 +231,33 @@
     3,
     174,
     2,
+    2,
     41,
-    51,
-    3,
     2,
     2,
+    51,
     2,
+    3,
     2,
     2,
-    3,
     2,
     3,
     16,
     2,
-    2,
-    2,
-    8,
     18,
+    8,
     2,
     17,
-    42,
-    7,
     3,
+    2,
+    4,
+    7,
     12,
     7,
-    4,
-    11,
     3,
+    3,
+    42,
+    11,
     100,
     13,
     100,
@@ -286,29 +287,29 @@
     28,
     3,
     6,
-    5,
-    7,
     3,
     6,
+    5,
+    7,
     4,
     2,
-    7,
     2,
     2,
+    6,
     2,
     2,
-    6,
+    7,
     20,
     2,
     9,
-    13,
-    4,
+    2,
     3,
+    13,
+    2,
     3,
     2,
     4,
-    2,
-    2,
+    4,
     2,
     2,
     2,
@@ -421,6 +422,7 @@
     1,
     1,
     2,
+    2,
     50,
     50,
     50,
@@ -436,11 +438,13 @@
     1,
     1,
     1,
+    1,
     2,
     2,
     2,
     2,
     77,
+    2,
     1,
     3,
     2,
@@ -500,19 +504,6 @@
     1,
     3,
     2,
-    9,
-    2,
-    1,
-    1,
-    1,
-    1,
-    1,
-    2,
-    2,
-    3,
-    2,
-    3,
-    4,
     2,
     3,
     3,
@@ -522,14 +513,14 @@
   ],
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "entailment",
     "1": "neutral",
     "2": "contradiction"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "contradiction": 2,
     "entailment": 0,
@@ -540,12 +531,12 @@
   "max_relative_positions": -1,
   "model_type": "deberta-v2",
   "norm_rel_ebd": "layer_norm",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "pooler_dropout": 0,
   "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 1024,
+  "pooler_hidden_size": 768,
   "pos_att_type": [
     "p2c",
     "c2p"
@@ -577,14 +568,14 @@
     "scitail/snli_format",
     "hans",
     "WANLI",
-    "recast/recast_megaveridicality",
-    "recast/recast_sentiment",
     "recast/recast_verbnet",
     "recast/recast_kg_relations",
-    "recast/recast_puns",
+    "recast/recast_ner",
     "recast/recast_factuality",
+    "recast/recast_puns",
+    "recast/recast_megaveridicality",
+    "recast/recast_sentiment",
     "recast/recast_verbcorner",
-    "recast/recast_ner",
     "probability_words_nli/usnli",
     "probability_words_nli/reasoning_1hop",
     "probability_words_nli/reasoning_2hop",
@@ -611,13 +602,13 @@
     "robust_nli_is_sd",
     "robust_nli_li_ts",
     "add_one_rte",
-    "imppres/implicature_gradable_adjective/log",
-    "imppres/implicature_numerals_2_3/log",
+    "imppres/implicature_numerals_10_100/log",
+    "imppres/implicature_connectives/log",
     "imppres/implicature_modals/log",
     "imppres/implicature_gradable_verb/log",
-    "imppres/implicature_numerals_10_100/log",
+    "imppres/implicature_gradable_adjective/log",
+    "imppres/implicature_numerals_2_3/log",
     "imppres/implicature_quantifiers/log",
-    "imppres/implicature_connectives/log",
     "glue_diagnostics/diagnostics",
     "hlgd",
     "paws/labeled_final",
@@ -626,109 +617,110 @@
     "conll2003/pos_tags",
     "conll2003/chunk_tags",
     "conll2003/ner_tags",
+    "hh-rlhf",
     "model-written-evals",
     "truthful_qa/multiple_choice",
     "fig-qa",
-    "bigbench/tracking_shuffled_objects",
-    "bigbench/color",
-    "bigbench/cause_and_effect",
+    "bigbench/physical_intuition",
+    "bigbench/authorship_verification",
+    "bigbench/implicit_relations",
     "bigbench/dyck_languages",
-    "bigbench/identify_math_theorems",
-    "bigbench/unit_interpretation",
-    "bigbench/arithmetic",
-    "bigbench/social_iqa",
-    "bigbench/penguins_in_a_table",
-    "bigbench/play_dialog_same_or_different",
     "bigbench/novel_concepts",
-    "bigbench/international_phonetic_alphabet_nli",
-    "bigbench/implicatures",
-    "bigbench/english_proverbs",
-    "bigbench/simple_ethical_questions",
+    "bigbench/moral_permissibility",
+    "bigbench/metaphor_understanding",
+    "bigbench/temporal_sequences",
     "bigbench/sports_understanding",
+    "bigbench/analytic_entailment",
+    "bigbench/social_support",
     "bigbench/emoji_movie",
-    "bigbench/implicit_relations",
+    "bigbench/dark_humor_detection",
+    "bigbench/suicide_risk",
+    "bigbench/fact_checker",
+    "bigbench/hhh_alignment",
+    "bigbench/formal_fallacies_syllogisms_negation",
+    "bigbench/bbq_lite_json",
+    "bigbench/cause_and_effect",
+    "bigbench/logic_grid_puzzle",
     "bigbench/empirical_judgments",
-    "bigbench/navigate",
-    "bigbench/logical_deduction",
-    "bigbench/reasoning_about_colored_objects",
-    "bigbench/snarks",
-    "bigbench/gre_reading_comprehension",
-    "bigbench/ruin_names",
-    "bigbench/analytic_entailment",
-    "bigbench/authorship_verification",
-    "bigbench/code_line_description",
-    "bigbench/logical_sequence",
-    "bigbench/disambiguation_qa",
+    "bigbench/human_organs_senses",
     "bigbench/misconceptions",
-    "bigbench/understanding_fables",
-    "bigbench/intent_recognition",
+    "bigbench/strange_stories",
+    "bigbench/logical_args",
+    "bigbench/known_unknowns",
+    "bigbench/cs_algorithms",
+    "bigbench/emojis_emotion_prediction",
+    "bigbench/cifar10_classification",
+    "bigbench/penguins_in_a_table",
     "bigbench/odd_one_out",
-    "bigbench/temporal_sequences",
+    "bigbench/intent_recognition",
+    "bigbench/physics",
+    "bigbench/conceptual_combinations",
+    "bigbench/logical_deduction",
+    "bigbench/causal_judgment",
+    "bigbench/winowhy",
+    "bigbench/arithmetic",
+    "bigbench/undo_permutation",
     "bigbench/analogical_similarity",
-    "bigbench/emojis_emotion_prediction",
+    "bigbench/social_iqa",
     "bigbench/key_value_maps",
-    "bigbench/identify_odd_metaphor",
-    "bigbench/geometric_shapes",
-    "bigbench/suicide_risk",
-    "bigbench/strategyqa",
-    "bigbench/logical_fallacy_detection",
-    "bigbench/known_unknowns",
-    "bigbench/social_support",
-    "bigbench/logic_grid_puzzle",
-    "bigbench/question_selection",
-    "bigbench/fact_checker",
-    "bigbench/moral_permissibility",
-    "bigbench/dark_humor_detection",
-    "bigbench/mathematical_induction",
-    "bigbench/movie_recommendation",
-    "bigbench/human_organs_senses",
-    "bigbench/vitaminc_fact_verification",
+    "bigbench/implicatures",
+    "bigbench/real_or_fake_text",
+    "bigbench/disambiguation_qa",
+    "bigbench/similarities_abstraction",
     "bigbench/movie_dialog_same_or_different",
-    "bigbench/metaphor_boolean",
-    "bigbench/causal_judgment",
-    "bigbench/epistemic_reasoning",
-    "bigbench/sentence_ambiguity",
-    "bigbench/logical_args",
+    "bigbench/english_proverbs",
+    "bigbench/presuppositions_as_nli",
+    "bigbench/entailed_polarity",
+    "bigbench/snarks",
+    "bigbench/goal_step_wikihow",
+    "bigbench/crass_ai",
+    "bigbench/play_dialog_same_or_different",
     "bigbench/hindu_knowledge",
-    "bigbench/cs_algorithms",
-    "bigbench/hhh_alignment",
-    "bigbench/physical_intuition",
-    "bigbench/crash_blossom",
-    "bigbench/cifar10_classification",
+    "bigbench/international_phonetic_alphabet_nli",
+    "bigbench/understanding_fables",
+    "bigbench/geometric_shapes",
+    "bigbench/code_line_description",
     "bigbench/riddle_sense",
-    "bigbench/hyperbaton",
-    "bigbench/general_knowledge",
-    "bigbench/anachronisms",
-    "bigbench/entailed_polarity",
-    "bigbench/nonsense_words_grammar",
-    "bigbench/mnist_ascii",
     "bigbench/symbol_interpretation",
-    "bigbench/figure_of_speech_detection",
-    "bigbench/abstract_narrative_understanding",
     "bigbench/irony_identification",
-    "bigbench/discourse_marker_prediction",
+    "bigbench/anachronisms",
+    "bigbench/navigate",
+    "bigbench/crash_blossom",
+    "bigbench/identify_odd_metaphor",
+    "bigbench/simple_ethical_questions",
+    "bigbench/contextual_parametric_knowledge_conflicts",
     "bigbench/date_understanding",
-    "bigbench/metaphor_understanding",
-    "bigbench/goal_step_wikihow",
-    "bigbench/similarities_abstraction",
+    "bigbench/figure_of_speech_detection",
+    "bigbench/question_selection",
+    "bigbench/elementary_math_qa",
+    "bigbench/nonsense_words_grammar",
     "bigbench/salient_translation_error_detection",
-    "bigbench/formal_fallacies_syllogisms_negation",
-    "bigbench/presuppositions_as_nli",
+    "bigbench/epistemic_reasoning",
+    "bigbench/movie_recommendation",
+    "bigbench/strategyqa",
+    "bigbench/tracking_shuffled_objects",
+    "bigbench/unit_interpretation",
+    "bigbench/reasoning_about_colored_objects",
+    "bigbench/discourse_marker_prediction",
+    "bigbench/logical_fallacy_detection",
+    "bigbench/general_knowledge",
+    "bigbench/abstract_narrative_understanding",
+    "bigbench/color",
+    "bigbench/hyperbaton",
+    "bigbench/logical_sequence",
+    "bigbench/mnist_ascii",
     "bigbench/fantasy_reasoning",
-    "bigbench/contextual_parametric_knowledge_conflicts",
-    "bigbench/evaluating_information_essentiality",
-    "bigbench/real_or_fake_text",
-    "bigbench/conceptual_combinations",
-    "bigbench/phrase_relatedness",
-    "bigbench/crass_ai",
-    "bigbench/undo_permutation",
-    "bigbench/physics",
+    "bigbench/mathematical_induction",
     "bigbench/timedial",
-    "bigbench/winowhy",
+    "bigbench/identify_math_theorems",
     "bigbench/checkmate_in_one",
-    "bigbench/bbq_lite_json",
-    "bigbench/strange_stories",
-    "bigbench/elementary_math_qa",
+    "bigbench/phrase_relatedness",
+    "bigbench/ruin_names",
+    "bigbench/gre_reading_comprehension",
+    "bigbench/metaphor_boolean",
+    "bigbench/sentence_ambiguity",
+    "bigbench/vitaminc_fact_verification",
+    "bigbench/evaluating_information_essentiality",
     "cos_e/v1.0",
     "cosmos_qa",
     "dream",
@@ -768,11 +760,11 @@
     "ethos/binary",
     "ethos/multilabel",
     "tweet_eval/sentiment",
-    "tweet_eval/offensive",
-    "tweet_eval/emoji",
-    "tweet_eval/emotion",
     "tweet_eval/irony",
+    "tweet_eval/offensive",
     "tweet_eval/hate",
+    "tweet_eval/emotion",
+    "tweet_eval/emoji",
     "tweet_eval/stance_abortion",
     "tweet_eval/stance_atheism",
     "tweet_eval/stance_climate",
@@ -780,33 +772,33 @@
     "tweet_eval/stance_hillary",
     "discovery/discovery",
     "pragmeval/squinky-informativeness",
+    "pragmeval/emobank-arousal",
     "pragmeval/switchboard",
+    "pragmeval/squinky-implicature",
+    "pragmeval/emobank-valence",
     "pragmeval/mrda",
+    "pragmeval/squinky-formality",
     "pragmeval/verifiability",
-    "pragmeval/emobank-arousal",
     "pragmeval/emobank-dominance",
-    "pragmeval/squinky-formality",
-    "pragmeval/squinky-implicature",
-    "pragmeval/emobank-valence",
+    "pragmeval/persuasiveness-specificity",
+    "pragmeval/persuasiveness-strength",
     "pragmeval/persuasiveness-claimtype",
-    "pragmeval/persuasiveness-eloquence",
-    "pragmeval/emergent",
     "pragmeval/pdtb",
-    "pragmeval/persuasiveness-strength",
-    "pragmeval/persuasiveness-relevance",
-    "pragmeval/persuasiveness-specificity",
-    "pragmeval/persuasiveness-premisetype",
-    "pragmeval/stac",
     "pragmeval/sarcasm",
+    "pragmeval/stac",
+    "pragmeval/persuasiveness-premisetype",
+    "pragmeval/persuasiveness-eloquence",
     "pragmeval/gum",
-    "silicone/oasis",
+    "pragmeval/emergent",
+    "pragmeval/persuasiveness-relevance",
+    "silicone/dyda_da",
+    "silicone/dyda_e",
+    "silicone/maptask",
     "silicone/meld_e",
     "silicone/meld_s",
-    "silicone/maptask",
-    "silicone/dyda_e",
-    "silicone/dyda_da",
-    "silicone/iemocap",
     "silicone/sem",
+    "silicone/oasis",
+    "silicone/iemocap",
     "lex_glue/eurlex",
     "lex_glue/scotus",
     "lex_glue/ledgar",
@@ -836,29 +828,29 @@
     "go_emotions/simplified",
     "scicite",
     "liar",
-    "lexical_relation_classification/CogALexV",
-    "lexical_relation_classification/EVALution",
     "lexical_relation_classification/ROOT09",
     "lexical_relation_classification/BLESS",
+    "lexical_relation_classification/CogALexV",
+    "lexical_relation_classification/EVALution",
     "lexical_relation_classification/K&H+N",
-    "linguisticprobing/odd_man_out",
-    "linguisticprobing/tree_depth",
     "linguisticprobing/coordination_inversion",
     "linguisticprobing/obj_number",
-    "linguisticprobing/bigram_shift",
     "linguisticprobing/past_present",
     "linguisticprobing/sentence_length",
-    "linguisticprobing/top_constituents",
     "linguisticprobing/subj_number",
+    "linguisticprobing/odd_man_out",
+    "linguisticprobing/tree_depth",
+    "linguisticprobing/top_constituents",
+    "linguisticprobing/bigram_shift",
     "crowdflower/political-media-message",
-    "crowdflower/text_emotion",
-    "crowdflower/corporate-messaging",
+    "crowdflower/political-media-audience",
     "crowdflower/economic-news",
+    "crowdflower/text_emotion",
+    "crowdflower/political-media-bias",
     "crowdflower/airline-sentiment",
     "crowdflower/tweet_global_warming",
+    "crowdflower/corporate-messaging",
     "crowdflower/sentiment_nuclear_power",
-    "crowdflower/political-media-audience",
-    "crowdflower/political-media-bias",
     "ethics/commonsense",
     "ethics/deontology",
     "ethics/justice",
@@ -921,8 +913,8 @@
     "scruples",
     "wouldyourather",
     "attempto-nli",
-    "defeasible-nli/atomic",
     "defeasible-nli/snli",
+    "defeasible-nli/atomic",
     "help-nli",
     "nli-veridicality-transitivity",
     "natural-language-satisfiability",
@@ -945,8 +937,8 @@
     "redefine-math",
     "puzzte",
     "implicatures",
-    "race/middle",
     "race/high",
+    "race/middle",
     "race-c",
     "spartqa-yn",
     "spartqa-mchoice",
@@ -967,12 +959,13 @@
     "chaos-mnli-ambiguity",
     "headline_cause/en_simple",
     "logiqa-2.0-nli",
-    "oasst2_dense_flat/quality",
-    "oasst2_dense_flat/toxicity",
-    "oasst2_dense_flat/helpfulness",
+    "oasst1_dense_flat/quality",
+    "oasst1_dense_flat/toxicity",
+    "oasst1_dense_flat/helpfulness",
+    "PARARULE-Plus",
     "mindgames",
-    "universal_dependencies/en_partut/deprel",
     "universal_dependencies/en_lines/deprel",
+    "universal_dependencies/en_partut/deprel",
     "universal_dependencies/en_ewt/deprel",
     "universal_dependencies/en_gum/deprel",
     "ambient",
@@ -986,11 +979,13 @@
     "civil_comments/sexual_explicit",
     "cloth",
     "dgen",
+    "oasst1_pairwise_rlhf_reward",
     "I2D2",
     "args_me",
     "Touche23-ValueEval",
     "starcon",
     "banking77",
+    "ruletaker",
     "lsat_qa/all",
     "ConTRoL-nli",
     "tracie",
@@ -1050,19 +1045,6 @@
     "ReSQ",
     "semantic_fragments_nli",
     "dataset_train_nli",
-    "stepgame",
-    "nlgraph",
-    "oasst2_pairwise_rlhf_reward",
-    "hh-rlhf/helpful-online",
-    "hh-rlhf/helpful-base",
-    "hh-rlhf/helpful-rejection-sampled",
-    "hh-rlhf/harmless-base",
-    "ruletaker",
-    "PARARULE-Plus",
-    "proofwriter",
-    "logical-entailment",
-    "nope",
-    "LogicNLI",
     "babi_nli",
     "gen_debiased_nli",
     "imppres/presupposition",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10ba2318838de3322df017b03413d90a4eb68ee7c7d1a3f899af6ea8e5c5ce39
-size 1740308548
+oid sha256:e71aa508566ef95b4f81d549f1f9eae2060bb676da926311e2be604052e4908f
+size 737722356