Upload 7 files

config.json

@@ -1,5 +1,5 @@
 {
- "_name_or_path": "sileod/deberta-v3-base-tasksource-nli",
+ "_name_or_path": "tasksource/deberta-base-long-nli",
  "architectures": [
  "DebertaV2ForSequenceClassification"
  ],
@@ -28,8 +28,8 @@
  2,
  3,
  2,
- 6,
  2,
+ 6,
  2,
  2,
  2,
@@ -68,15 +68,10 @@
  3,
  3,
  3,
- 3,
  2,
  2,
  2,
  2,
- 47,
- 23,
- 9,
- 1,
  1,
  1,
  1,
@@ -218,12 +213,12 @@
  4,
  2,
  8,
- 3,
+ 20,
  2,
+ 4,
  2,
  2,
- 4,
- 20,
+ 3,
  3,
  3,
  3,
@@ -231,33 +226,33 @@
  3,
  174,
  2,
- 2,
  41,
+ 3,
+ 51,
  2,
  2,
- 51,
  2,
- 3,
  2,
  2,
  2,
- 3,
  16,
+ 3,
  2,
- 18,
  8,
  2,
+ 2,
+ 18,
+ 2,
  17,
  3,
- 2,
- 4,
+ 3,
  7,
+ 11,
  12,
  7,
- 3,
- 3,
+ 4,
  42,
- 11,
+ 3,
  100,
  13,
  100,
@@ -287,42 +282,37 @@
  28,
  3,
  6,
- 3,
- 6,
- 5,
  7,
+ 3,
  4,
+ 5,
+ 6,
  2,
  2,
  2,
  6,
+ 20,
+ 7,
  2,
  2,
- 7,
- 20,
  2,
  9,
- 2,
- 3,
  13,
  2,
  3,
- 2,
  4,
+ 3,
+ 2,
  4,
  2,
  2,
  2,
  2,
+ 2,
  4,
  1,
  2,
  1,
- 13,
- 3,
- 5,
- 11,
- 37,
  2,
  49,
  40,
@@ -371,8 +361,6 @@
  1,
  2,
  1,
- 3,
- 2,
  2,
  2,
  2,
@@ -423,12 +411,6 @@
  1,
  2,
  2,
- 50,
- 50,
- 50,
- 50,
- 2,
- 1,
  1,
  1,
  1,
@@ -444,22 +426,12 @@
  2,
  2,
  77,
- 2,
- 1,
  3,
  2,
  2,
  1,
  1,
  2,
- 2,
- 2,
- 2,
- 2,
- 2,
- 2,
- 2,
- 2,
  3,
  18,
  13,
@@ -468,13 +440,9 @@
  2,
  2,
  2,
- 2,
  4,
  2,
  24,
- 23,
- 67,
- 279,
  3,
  2,
  2,
@@ -494,6 +462,7 @@
  1,
  17,
  3,
+ 3,
  2,
  3,
  2,
@@ -504,11 +473,66 @@
  1,
  3,
  2,
+ 9,
+ 2,
+ 1,
+ 1,
+ 1,
+ 1,
+ 1,
+ 2,
  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,
+ 3,
+ 3,
+ 3,
  1
  ],
  "hidden_act": "gelu",
@@ -527,7 +551,7 @@
  "neutral": 1
  },
  "layer_norm_eps": 1e-07,
- "max_position_embeddings": 512,
+ "max_position_embeddings": 1280,
  "max_relative_positions": -1,
  "model_type": "deberta-v2",
  "norm_rel_ebd": "layer_norm",
@@ -568,18 +592,18 @@
  "scitail/snli_format",
  "hans",
  "WANLI",
- "recast/recast_verbnet",
+ "recast/recast_puns",
+ "recast/recast_factuality",
  "recast/recast_kg_relations",
+ "recast/recast_verbnet",
+ "recast/recast_verbcorner",
  "recast/recast_ner",
- "recast/recast_factuality",
- "recast/recast_puns",
  "recast/recast_megaveridicality",
  "recast/recast_sentiment",
- "recast/recast_verbcorner",
- "probability_words_nli/usnli",
  "probability_words_nli/reasoning_1hop",
+ "probability_words_nli/usnli",
  "probability_words_nli/reasoning_2hop",
- "nan-nli/joey234--nan-nli",
+ "nan-nli",
  "nli_fever",
  "breaking_nli",
  "conj_nli",
@@ -602,125 +626,120 @@
  "robust_nli_is_sd",
  "robust_nli_li_ts",
  "add_one_rte",
+ "imppres/implicature_gradable_adjective/log",
+ "imppres/implicature_modals/log",
  "imppres/implicature_numerals_10_100/log",
+ "imppres/implicature_quantifiers/log",
  "imppres/implicature_connectives/log",
- "imppres/implicature_modals/log",
  "imppres/implicature_gradable_verb/log",
- "imppres/implicature_gradable_adjective/log",
  "imppres/implicature_numerals_2_3/log",
- "imppres/implicature_quantifiers/log",
- "glue_diagnostics/diagnostics",
  "hlgd",
  "paws/labeled_final",
  "paws/labeled_swap",
  "medical_questions_pairs",
- "conll2003/pos_tags",
- "conll2003/chunk_tags",
- "conll2003/ner_tags",
- "hh-rlhf",
  "model-written-evals",
  "truthful_qa/multiple_choice",
  "fig-qa",
+ "bigbench/discourse_marker_prediction",
+ "bigbench/gre_reading_comprehension",
+ "bigbench/simple_ethical_questions",
+ "bigbench/known_unknowns",
+ "bigbench/fact_checker",
+ "bigbench/phrase_relatedness",
+ "bigbench/irony_identification",
+ "bigbench/crash_blossom",
  "bigbench/physical_intuition",
- "bigbench/authorship_verification",
- "bigbench/implicit_relations",
- "bigbench/dyck_languages",
- "bigbench/novel_concepts",
- "bigbench/moral_permissibility",
- "bigbench/metaphor_understanding",
- "bigbench/temporal_sequences",
- "bigbench/sports_understanding",
  "bigbench/analytic_entailment",
- "bigbench/social_support",
- "bigbench/emoji_movie",
- "bigbench/dark_humor_detection",
- "bigbench/suicide_risk",
- "bigbench/fact_checker",
+ "bigbench/play_dialog_same_or_different",
+ "bigbench/metaphor_boolean",
+ "bigbench/undo_permutation",
+ "bigbench/disambiguation_qa",
+ "bigbench/metaphor_understanding",
+ "bigbench/nonsense_words_grammar",
+ "bigbench/logical_deduction",
+ "bigbench/sentence_ambiguity",
+ "bigbench/key_value_maps",
+ "bigbench/checkmate_in_one",
+ "bigbench/code_line_description",
+ "bigbench/crass_ai",
+ "bigbench/movie_dialog_same_or_different",
+ "bigbench/strategyqa",
  "bigbench/hhh_alignment",
- "bigbench/formal_fallacies_syllogisms_negation",
- "bigbench/bbq_lite_json",
- "bigbench/cause_and_effect",
- "bigbench/logic_grid_puzzle",
- "bigbench/empirical_judgments",
- "bigbench/human_organs_senses",
- "bigbench/misconceptions",
- "bigbench/strange_stories",
- "bigbench/logical_args",
- "bigbench/known_unknowns",
+ "bigbench/english_proverbs",
  "bigbench/cs_algorithms",
- "bigbench/emojis_emotion_prediction",
- "bigbench/cifar10_classification",
- "bigbench/penguins_in_a_table",
- "bigbench/odd_one_out",
- "bigbench/intent_recognition",
- "bigbench/physics",
+ "bigbench/formal_fallacies_syllogisms_negation",
  "bigbench/conceptual_combinations",
- "bigbench/logical_deduction",
- "bigbench/causal_judgment",
- "bigbench/winowhy",
+ "bigbench/geometric_shapes",
+ "bigbench/tracking_shuffled_objects",
  "bigbench/arithmetic",
- "bigbench/undo_permutation",
- "bigbench/analogical_similarity",
+ "bigbench/misconceptions",
+ "bigbench/odd_one_out",
+ "bigbench/international_phonetic_alphabet_nli",
  "bigbench/social_iqa",
- "bigbench/key_value_maps",
- "bigbench/implicatures",
- "bigbench/real_or_fake_text",
- "bigbench/disambiguation_qa",
+ "bigbench/logical_fallacy_detection",
+ "bigbench/hyperbaton",
+ "bigbench/novel_concepts",
  "bigbench/similarities_abstraction",
- "bigbench/movie_dialog_same_or_different",
- "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/international_phonetic_alphabet_nli",
- "bigbench/understanding_fables",
- "bigbench/geometric_shapes",
- "bigbench/code_line_description",
+ "bigbench/timedial",
+ "bigbench/salient_translation_error_detection",
+ "bigbench/cifar10_classification",
+ "bigbench/winowhy",
+ "bigbench/mathematical_induction",
+ "bigbench/real_or_fake_text",
+ "bigbench/epistemic_reasoning",
  "bigbench/riddle_sense",
- "bigbench/symbol_interpretation",
- "bigbench/irony_identification",
+ "bigbench/identify_odd_metaphor",
+ "bigbench/human_organs_senses",
+ "bigbench/emojis_emotion_prediction",
+ "bigbench/logical_args",
  "bigbench/anachronisms",
+ "bigbench/bbq_lite_json",
+ "bigbench/general_knowledge",
+ "bigbench/logical_sequence",
  "bigbench/navigate",
- "bigbench/crash_blossom",
- "bigbench/identify_odd_metaphor",
- "bigbench/simple_ethical_questions",
- "bigbench/contextual_parametric_knowledge_conflicts",
+ "bigbench/analogical_similarity",
+ "bigbench/authorship_verification",
+ "bigbench/elementary_math_qa",
+ "bigbench/goal_step_wikihow",
+ "bigbench/empirical_judgments",
+ "bigbench/question_selection",
+ "bigbench/temporal_sequences",
+ "bigbench/mnist_ascii",
+ "bigbench/color",
  "bigbench/date_understanding",
  "bigbench/figure_of_speech_detection",
- "bigbench/question_selection",
- "bigbench/elementary_math_qa",
- "bigbench/nonsense_words_grammar",
- "bigbench/salient_translation_error_detection",
- "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/contextual_parametric_knowledge_conflicts",
+ "bigbench/ruin_names",
  "bigbench/abstract_narrative_understanding",
- "bigbench/color",
- "bigbench/hyperbaton",
- "bigbench/logical_sequence",
- "bigbench/mnist_ascii",
- "bigbench/fantasy_reasoning",
- "bigbench/mathematical_induction",
- "bigbench/timedial",
+ "bigbench/physics",
+ "bigbench/understanding_fables",
  "bigbench/identify_math_theorems",
- "bigbench/checkmate_in_one",
- "bigbench/phrase_relatedness",
- "bigbench/ruin_names",
- "bigbench/gre_reading_comprehension",
- "bigbench/metaphor_boolean",
- "bigbench/sentence_ambiguity",
+ "bigbench/penguins_in_a_table",
  "bigbench/vitaminc_fact_verification",
+ "bigbench/social_support",
+ "bigbench/strange_stories",
+ "bigbench/dark_humor_detection",
+ "bigbench/fantasy_reasoning",
+ "bigbench/logic_grid_puzzle",
+ "bigbench/emoji_movie",
+ "bigbench/moral_permissibility",
+ "bigbench/symbol_interpretation",
+ "bigbench/presuppositions_as_nli",
+ "bigbench/dyck_languages",
+ "bigbench/implicatures",
+ "bigbench/suicide_risk",
+ "bigbench/unit_interpretation",
+ "bigbench/intent_recognition",
+ "bigbench/movie_recommendation",
+ "bigbench/snarks",
  "bigbench/evaluating_information_essentiality",
+ "bigbench/sports_understanding",
+ "bigbench/entailed_polarity",
+ "bigbench/causal_judgment",
+ "bigbench/cause_and_effect",
+ "bigbench/implicit_relations",
+ "bigbench/reasoning_about_colored_objects",
+ "bigbench/hindu_knowledge",
  "cos_e/v1.0",
  "cosmos_qa",
  "dream",
@@ -741,8 +760,8 @@
  "art",
  "winogrande/winogrande_xl",
  "codah/codah",
- "ai2_arc/ARC-Challenge/challenge",
  "ai2_arc/ARC-Easy/challenge",
+ "ai2_arc/ARC-Challenge/challenge",
  "definite_pronoun_resolution",
  "swag/regular",
  "math_qa",
@@ -754,51 +773,51 @@
  "toxic_conversations",
  "TuringBench",
  "trec",
- "vitaminc/tals--vitaminc",
+ "vitaminc",
  "hope_edi/english",
  "rumoureval_2019/RumourEval2019",
  "ethos/binary",
  "ethos/multilabel",
- "tweet_eval/sentiment",
- "tweet_eval/irony",
+ "tweet_eval/emoji",
  "tweet_eval/offensive",
- "tweet_eval/hate",
  "tweet_eval/emotion",
- "tweet_eval/emoji",
+ "tweet_eval/hate",
+ "tweet_eval/irony",
+ "tweet_eval/sentiment",
  "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/emobank-arousal",
- "pragmeval/switchboard",
- "pragmeval/squinky-implicature",
- "pragmeval/emobank-valence",
- "pragmeval/mrda",
  "pragmeval/squinky-formality",
+ "pragmeval/switchboard",
  "pragmeval/verifiability",
+ "pragmeval/mrda",
+ "pragmeval/squinky-informativeness",
+ "pragmeval/squinky-implicature",
+ "pragmeval/emobank-arousal",
  "pragmeval/emobank-dominance",
- "pragmeval/persuasiveness-specificity",
- "pragmeval/persuasiveness-strength",
- "pragmeval/persuasiveness-claimtype",
- "pragmeval/pdtb",
+ "pragmeval/emobank-valence",
  "pragmeval/sarcasm",
- "pragmeval/stac",
+ "pragmeval/pdtb",
+ "pragmeval/persuasiveness-claimtype",
+ "pragmeval/persuasiveness-relevance",
  "pragmeval/persuasiveness-premisetype",
  "pragmeval/persuasiveness-eloquence",
+ "pragmeval/persuasiveness-strength",
+ "pragmeval/stac",
+ "pragmeval/persuasiveness-specificity",
  "pragmeval/gum",
  "pragmeval/emergent",
- "pragmeval/persuasiveness-relevance",
- "silicone/dyda_da",
- "silicone/dyda_e",
- "silicone/maptask",
- "silicone/meld_e",
- "silicone/meld_s",
  "silicone/sem",
- "silicone/oasis",
+ "silicone/meld_e",
  "silicone/iemocap",
+ "silicone/maptask",
+ "silicone/dyda_e",
+ "silicone/dyda_da",
+ "silicone/oasis",
+ "silicone/meld_s",
  "lex_glue/eurlex",
  "lex_glue/scotus",
  "lex_glue/ledgar",
@@ -828,29 +847,29 @@
  "go_emotions/simplified",
  "scicite",
  "liar",
- "lexical_relation_classification/ROOT09",
- "lexical_relation_classification/BLESS",
- "lexical_relation_classification/CogALexV",
  "lexical_relation_classification/EVALution",
+ "lexical_relation_classification/ROOT09",
  "lexical_relation_classification/K&H+N",
- "linguisticprobing/coordination_inversion",
- "linguisticprobing/obj_number",
+ "lexical_relation_classification/CogALexV",
+ "lexical_relation_classification/BLESS",
+ "linguisticprobing/subj_number",
  "linguisticprobing/past_present",
+ "linguisticprobing/obj_number",
  "linguisticprobing/sentence_length",
- "linguisticprobing/subj_number",
- "linguisticprobing/odd_man_out",
- "linguisticprobing/tree_depth",
  "linguisticprobing/top_constituents",
+ "linguisticprobing/tree_depth",
+ "linguisticprobing/coordination_inversion",
+ "linguisticprobing/odd_man_out",
  "linguisticprobing/bigram_shift",
  "crowdflower/political-media-message",
+ "crowdflower/text_emotion",
  "crowdflower/political-media-audience",
  "crowdflower/economic-news",
- "crowdflower/text_emotion",
- "crowdflower/political-media-bias",
+ "crowdflower/corporate-messaging",
  "crowdflower/airline-sentiment",
  "crowdflower/tweet_global_warming",
- "crowdflower/corporate-messaging",
  "crowdflower/sentiment_nuclear_power",
+ "crowdflower/political-media-bias",
  "ethics/commonsense",
  "ethics/deontology",
  "ethics/justice",
@@ -859,11 +878,6 @@
  "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",
@@ -877,13 +891,13 @@
  "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",
@@ -912,12 +926,10 @@
  "synthetic-instruct-gptj-pairwise",
  "scruples",
  "wouldyourather",
- "attempto-nli",
- "defeasible-nli/snli",
  "defeasible-nli/atomic",
+ "defeasible-nli/snli",
  "help-nli",
  "nli-veridicality-transitivity",
- "natural-language-satisfiability",
  "lonli",
  "dadc-limit-nli",
  "FLUTE",
@@ -959,15 +971,10 @@
  "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",
+ "oasst2_dense_flat/quality",
+ "oasst2_dense_flat/toxicity",
+ "oasst2_dense_flat/helpfulness",
  "mindgames",
- "universal_dependencies/en_lines/deprel",
- "universal_dependencies/en_partut/deprel",
- "universal_dependencies/en_ewt/deprel",
- "universal_dependencies/en_gum/deprel",
  "ambient",
  "path-naturalness-prediction",
  "civil_comments/toxicity",
@@ -979,28 +986,17 @@
  "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",
@@ -1009,13 +1005,9 @@
  "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",
@@ -1034,7 +1026,8 @@
  "esci",
  "chatbot_arena_conversations",
  "dnd_style_intents",
- "FLD.v2",
+ "FLD.v2/default",
+ "FLD.v2/star",
  "SDOH-NLI",
  "scifact_entailment",
  "feasibilityQA",
@@ -1045,15 +1038,70 @@
  "ReSQ",
  "semantic_fragments_nli",
  "dataset_train_nli",
+ "stepgame",
+ "nlgraph",
+ "oasst2_pairwise_rlhf_reward",
+ "hh-rlhf/helpful-online",
+ "hh-rlhf/helpful-rejection-sampled",
+ "hh-rlhf/helpful-base",
+ "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/SP",
+ "brainteasers/WP",
+ "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",
  "babi_nli",
  "gen_debiased_nli",
  "imppres/presupposition",
  "/prag",
- "blimp-2",
- "mmlu-4"
+ "blimp-2"
  ],
  "torch_dtype": "float32",
- "transformers_version": "4.40.2",
+ "transformers_version": "4.45.2",
  "type_vocab_size": 0,
  "vocab_size": 128100
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab2e0c8ce7b17e5da51a9f8730c4189da5f86756462399c2408b28beb21d6785
+oid sha256:ec79161279746937d440ec246eab9237f18f326059f1831201a5922b23474058
 size 737722356

tokenizer.json

@@ -2,13 +2,13 @@
  "version": "1.0",
  "truncation": {
  "direction": "Right",
- "max_length": 256,
+ "max_length": 1280,
  "strategy": "LongestFirst",
  "stride": 0
  },
  "padding": {
  "strategy": {
- "Fixed": 256
+ "Fixed": 1280
  },
  "direction": "Right",
  "pad_to_multiple_of": null,

tokenizer_config.json

@@ -47,7 +47,7 @@
  "do_lower_case": false,
  "eos_token": "[SEP]",
  "mask_token": "[MASK]",
- "max_length": 256,
+ "max_length": 1280,
  "model_max_length": 1000000000000000019884624838656,
  "pad_to_multiple_of": null,
  "pad_token": "[PAD]",