five

kowndinya23/bigbench_zero_shot

收藏
Hugging Face2024-03-18 更新2024-06-11 收录
下载链接：
https://hf-mirror.com/datasets/kowndinya23/bigbench_zero_shot
下载链接
链接失效反馈
官方服务：
资源简介：
--- dataset_info: - config_name: abstract_narrative_understanding features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 6560069 num_examples: 3000 - name: train num_bytes: 5249819 num_examples: 2400 - name: validation num_bytes: 1310250 num_examples: 600 download_size: 1435670 dataset_size: 13120138 - config_name: anachronisms features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 48826 num_examples: 230 - name: train num_bytes: 39116 num_examples: 184 - name: validation num_bytes: 9710 num_examples: 46 download_size: 40931 dataset_size: 97652 - config_name: analogical_similarity features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 1373815 num_examples: 323 - name: train num_bytes: 1101512 num_examples: 259 - name: validation num_bytes: 272303 num_examples: 64 download_size: 285403 dataset_size: 2747630 - config_name: analytic_entailment features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 17316 num_examples: 70 - name: train num_bytes: 13368 num_examples: 54 - name: validation num_bytes: 3948 num_examples: 16 download_size: 21156 dataset_size: 34632 - config_name: arithmetic features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 3833272 num_examples: 15023 - name: train num_bytes: 3066775 num_examples: 12019 - name: validation num_bytes: 766497 num_examples: 3004 download_size: 2777853 dataset_size: 7666544 - config_name: ascii_word_recognition features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 4984662 num_examples: 5000 - name: train num_bytes: 3997273 num_examples: 4000 - name: validation num_bytes: 987389 num_examples: 1000 download_size: 2290165 dataset_size: 9969324 - config_name: authorship_verification features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 14118592 num_examples: 880 - name: train num_bytes: 11288481 num_examples: 704 - name: validation num_bytes: 2830111 num_examples: 176 download_size: 17714673 dataset_size: 28237184 - config_name: auto_categorization features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 40549 num_examples: 328 - name: train num_bytes: 32992 num_examples: 263 - name: validation num_bytes: 7557 num_examples: 65 download_size: 50064 dataset_size: 81098 - config_name: auto_debugging features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 5284 num_examples: 34 - name: train num_bytes: 2763 num_examples: 18 - name: validation num_bytes: 2521 num_examples: 16 download_size: 16180 dataset_size: 10568 - config_name: bbq_lite_json features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 6890493 num_examples: 16076 - name: train num_bytes: 5508584 num_examples: 12866 - name: validation num_bytes: 1381909 num_examples: 3210 download_size: 2208854 dataset_size: 13780986 - config_name: bridging_anaphora_resolution_barqa features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 1971015 num_examples: 648 - name: train num_bytes: 1537264 num_examples: 519 - name: validation num_bytes: 433751 num_examples: 129 download_size: 2143230 dataset_size: 3942030 - config_name: causal_judgment features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 204878 num_examples: 190 - name: train num_bytes: 164940 num_examples: 152 - name: validation num_bytes: 39938 num_examples: 38 download_size: 136495 dataset_size: 409756 - config_name: cause_and_effect features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 49314 num_examples: 153 - name: train num_bytes: 39620 num_examples: 123 - name: validation num_bytes: 9694 num_examples: 30 download_size: 37016 dataset_size: 98628 - config_name: checkmate_in_one features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 3123256 num_examples: 3498 - name: train num_bytes: 2502314 num_examples: 2799 - name: validation num_bytes: 620942 num_examples: 699 download_size: 2227113 dataset_size: 6246512 - config_name: chess_state_tracking features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 3269932 num_examples: 6000 - name: train num_bytes: 2616294 num_examples: 4800 - name: validation num_bytes: 653638 num_examples: 1200 download_size: 2064226 dataset_size: 6539864 - config_name: chinese_remainder_theorem features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 153222 num_examples: 500 - name: train num_bytes: 122601 num_examples: 400 - name: validation num_bytes: 30621 num_examples: 100 download_size: 85693 dataset_size: 306444 - config_name: cifar10_classification features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 111022200 num_examples: 20000 - name: train num_bytes: 88782724 num_examples: 16000 - name: validation num_bytes: 22239476 num_examples: 4000 download_size: 179818834 dataset_size: 222044400 - config_name: code_line_description features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 33670 num_examples: 60 - name: train num_bytes: 25530 num_examples: 44 - name: validation num_bytes: 8140 num_examples: 16 download_size: 42348 dataset_size: 67340 - config_name: codenames features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 25195 num_examples: 85 - name: train num_bytes: 19964 num_examples: 68 - name: validation num_bytes: 5231 num_examples: 17 download_size: 31257 dataset_size: 50390 - config_name: color features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 1633263 num_examples: 4000 - name: train num_bytes: 1306663 num_examples: 3200 - name: validation num_bytes: 326600 num_examples: 800 download_size: 301045 dataset_size: 3266526 - config_name: common_morpheme features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 12388 num_examples: 50 - name: train num_bytes: 8444 num_examples: 34 - name: validation num_bytes: 3944 num_examples: 16 download_size: 25122 dataset_size: 24776 - config_name: conceptual_combinations features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 58859 num_examples: 103 - name: train num_bytes: 48010 num_examples: 84 - name: validation num_bytes: 10849 num_examples: 19 download_size: 72767 dataset_size: 117718 - config_name: conlang_translation features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 215190 num_examples: 164 - name: train num_bytes: 173024 num_examples: 132 - name: validation num_bytes: 42166 num_examples: 32 download_size: 78115 dataset_size: 430380 - config_name: contextual_parametric_knowledge_conflicts features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 14587554 num_examples: 17528 - name: train num_bytes: 11666236 num_examples: 14023 - name: validation num_bytes: 2921318 num_examples: 3505 download_size: 16791080 dataset_size: 29175108 - config_name: crash_blossom features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 12194 num_examples: 38 - name: train num_bytes: 6999 num_examples: 22 - name: validation num_bytes: 5195 num_examples: 16 download_size: 19382 dataset_size: 24388 - config_name: crass_ai features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 22870 num_examples: 44 - name: train num_bytes: 14130 num_examples: 28 - name: validation num_bytes: 8740 num_examples: 16 download_size: 35821 dataset_size: 45740 - config_name: cryobiology_spanish features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 38674 num_examples: 146 - name: train num_bytes: 31129 num_examples: 117 - name: validation num_bytes: 7545 num_examples: 29 download_size: 47343 dataset_size: 77348 - config_name: cryptonite features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 2844402 num_examples: 26157 - name: train num_bytes: 2275724 num_examples: 20926 - name: validation num_bytes: 568678 num_examples: 5231 download_size: 2823789 dataset_size: 5688804 - config_name: cs_algorithms features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 272435 num_examples: 1320 - name: train num_bytes: 218192 num_examples: 1056 - name: validation num_bytes: 54243 num_examples: 264 download_size: 103967 dataset_size: 544870 - config_name: dark_humor_detection features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 26556 num_examples: 80 - name: train num_bytes: 21267 num_examples: 64 - name: validation num_bytes: 5289 num_examples: 16 download_size: 29248 dataset_size: 53112 - config_name: date_understanding features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 94908 num_examples: 369 - name: train num_bytes: 76165 num_examples: 296 - name: validation num_bytes: 18743 num_examples: 73 download_size: 61477 dataset_size: 189816 - config_name: disambiguation_qa features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 122471 num_examples: 258 - name: train num_bytes: 98687 num_examples: 207 - name: validation num_bytes: 23784 num_examples: 51 download_size: 57669 dataset_size: 244942 - config_name: discourse_marker_prediction features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 2090684 num_examples: 857 - name: train num_bytes: 1666052 num_examples: 686 - name: validation num_bytes: 424632 num_examples: 171 download_size: 1014595 dataset_size: 4181368 - config_name: disfl_qa features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 7964775 num_examples: 8000 - name: train num_bytes: 6376511 num_examples: 6400 - name: validation num_bytes: 1588264 num_examples: 1600 download_size: 9317097 dataset_size: 15929550 - config_name: dyck_languages features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 1227916 num_examples: 1000 - name: train num_bytes: 982680 num_examples: 800 - name: validation num_bytes: 245236 num_examples: 200 download_size: 106411 dataset_size: 2455832 - config_name: elementary_math_qa features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 13442550 num_examples: 38160 - name: train num_bytes: 10766969 num_examples: 30531 - name: validation num_bytes: 2675581 num_examples: 7629 download_size: 9860060 dataset_size: 26885100 - config_name: emoji_movie features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 33667 num_examples: 100 - name: train num_bytes: 26987 num_examples: 80 - name: validation num_bytes: 6680 num_examples: 20 download_size: 42501 dataset_size: 67334 - config_name: emojis_emotion_prediction features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 47983 num_examples: 131 - name: train num_bytes: 38458 num_examples: 105 - name: validation num_bytes: 9525 num_examples: 26 download_size: 20394 dataset_size: 95966 - config_name: empirical_judgments features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 47499 num_examples: 99 - name: train num_bytes: 38346 num_examples: 80 - name: validation num_bytes: 9153 num_examples: 19 download_size: 29317 dataset_size: 94998 - config_name: english_proverbs features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 22530 num_examples: 34 - name: train num_bytes: 12066 num_examples: 18 - name: validation num_bytes: 10464 num_examples: 16 download_size: 46557 dataset_size: 45060 - config_name: english_russian_proverbs features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 59900 num_examples: 80 - name: train num_bytes: 48051 num_examples: 64 - name: validation num_bytes: 11849 num_examples: 16 download_size: 75116 dataset_size: 119800 - config_name: entailed_polarity features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 25421 num_examples: 148 - name: train num_bytes: 20350 num_examples: 119 - name: validation num_bytes: 5071 num_examples: 29 download_size: 23255 dataset_size: 50842 - config_name: entailed_polarity_hindi features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 57052 num_examples: 138 - name: train num_bytes: 45829 num_examples: 111 - name: validation num_bytes: 11223 num_examples: 27 download_size: 35314 dataset_size: 114104 - config_name: epistemic_reasoning features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 887158 num_examples: 2000 - name: train num_bytes: 710107 num_examples: 1600 - name: validation num_bytes: 177051 num_examples: 400 download_size: 397293 dataset_size: 1774316 - config_name: evaluating_information_essentiality features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 77488 num_examples: 68 - name: train num_bytes: 59596 num_examples: 52 - name: validation num_bytes: 17892 num_examples: 16 download_size: 46943 dataset_size: 154976 - config_name: fact_checker features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 1337384 num_examples: 7154 - name: train num_bytes: 1070750 num_examples: 5724 - name: validation num_bytes: 266634 num_examples: 1430 download_size: 743981 dataset_size: 2674768 - config_name: fantasy_reasoning features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 75886 num_examples: 201 - name: train num_bytes: 61398 num_examples: 161 - name: validation num_bytes: 14488 num_examples: 40 download_size: 59562 dataset_size: 151772 - config_name: few_shot_nlg features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 75937 num_examples: 153 - name: train num_bytes: 61862 num_examples: 123 - name: validation num_bytes: 14075 num_examples: 30 download_size: 73220 dataset_size: 151874 - config_name: figure_of_speech_detection features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 21717 num_examples: 59 - name: train num_bytes: 15962 num_examples: 43 - name: validation num_bytes: 5755 num_examples: 16 download_size: 21305 dataset_size: 43434 - config_name: formal_fallacies_syllogisms_negation features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 8314653 num_examples: 14200 - name: train num_bytes: 6652955 num_examples: 11360 - name: validation num_bytes: 1661698 num_examples: 2840 download_size: 3702822 dataset_size: 16629306 - config_name: gem features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 36065281 num_examples: 14802 - name: train num_bytes: 28819497 num_examples: 11845 - name: validation num_bytes: 7245784 num_examples: 2957 download_size: 41114913 dataset_size: 72130562 - config_name: gender_inclusive_sentences_german features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 126881 num_examples: 200 - name: train num_bytes: 100628 num_examples: 160 - name: validation num_bytes: 26253 num_examples: 40 download_size: 120836 dataset_size: 253762 - config_name: general_knowledge features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 21828 num_examples: 70 - name: train num_bytes: 16818 num_examples: 54 - name: validation num_bytes: 5010 num_examples: 16 download_size: 28772 dataset_size: 43656 - config_name: geometric_shapes features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 180094 num_examples: 359 - name: train num_bytes: 144602 num_examples: 288 - name: validation num_bytes: 35492 num_examples: 71 download_size: 74610 dataset_size: 360188 - config_name: goal_step_wikihow features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 3567615 num_examples: 7053 - name: train num_bytes: 2853871 num_examples: 5643 - name: validation num_bytes: 713744 num_examples: 1410 download_size: 3717406 dataset_size: 7135230 - config_name: gre_reading_comprehension features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 94273 num_examples: 31 - name: train num_bytes: 44458 num_examples: 15 - name: validation num_bytes: 49815 num_examples: 16 download_size: 121735 dataset_size: 188546 - config_name: hhh_alignment features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 272898 num_examples: 221 - name: train num_bytes: 212488 num_examples: 179 - name: validation num_bytes: 60410 num_examples: 42 download_size: 192889 dataset_size: 545796 - config_name: hindi_question_answering features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 15154954 num_examples: 6610 - name: train num_bytes: 11983837 num_examples: 5288 - name: validation num_bytes: 3171117 num_examples: 1322 download_size: 10768233 dataset_size: 30309908 - config_name: hindu_knowledge features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 44092 num_examples: 175 - name: train num_bytes: 35392 num_examples: 140 - name: validation num_bytes: 8700 num_examples: 35 download_size: 49967 dataset_size: 88184 - config_name: hinglish_toxicity features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 60613 num_examples: 200 - name: train num_bytes: 49997 num_examples: 160 - name: validation num_bytes: 10616 num_examples: 40 download_size: 79649 dataset_size: 121226 - config_name: human_organs_senses features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 7944 num_examples: 42 - name: train num_bytes: 4873 num_examples: 26 - name: validation num_bytes: 3071 num_examples: 16 download_size: 16316 dataset_size: 15888 - config_name: hyperbaton features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 9383986 num_examples: 50000 - name: train num_bytes: 7509334 num_examples: 40000 - name: validation num_bytes: 1874652 num_examples: 10000 download_size: 4047743 dataset_size: 18767972 - config_name: identify_math_theorems features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 104841 num_examples: 53 - name: train num_bytes: 70295 num_examples: 37 - name: validation num_bytes: 34546 num_examples: 16 download_size: 82730 dataset_size: 209682 - config_name: identify_odd_metaphor features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 27602 num_examples: 47 - name: train num_bytes: 18138 num_examples: 31 - name: validation num_bytes: 9464 num_examples: 16 download_size: 45155 dataset_size: 55204 - config_name: implicatures features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 91683 num_examples: 492 - name: train num_bytes: 73416 num_examples: 394 - name: validation num_bytes: 18267 num_examples: 98 download_size: 68790 dataset_size: 183366 - config_name: implicit_relations features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 79710 num_examples: 85 - name: train num_bytes: 64346 num_examples: 68 - name: validation num_bytes: 15364 num_examples: 17 download_size: 51718 dataset_size: 159420 - config_name: indic_cause_and_effect features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 525910 num_examples: 585 - name: train num_bytes: 412281 num_examples: 468 - name: validation num_bytes: 113629 num_examples: 117 download_size: 230789 dataset_size: 1051820 - config_name: intent_recognition features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 322371 num_examples: 693 - name: train num_bytes: 257864 num_examples: 555 - name: validation num_bytes: 64507 num_examples: 138 download_size: 95825 dataset_size: 644742 - config_name: international_phonetic_alphabet_nli features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 79320 num_examples: 126 - name: train num_bytes: 63288 num_examples: 101 - name: validation num_bytes: 16032 num_examples: 25 download_size: 60049 dataset_size: 158640 - config_name: international_phonetic_alphabet_transliterate features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 275938 num_examples: 1003 - name: train num_bytes: 220784 num_examples: 803 - name: validation num_bytes: 55154 num_examples: 200 download_size: 243543 dataset_size: 551876 - config_name: intersect_geometry features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 211674752 num_examples: 249999 - name: train num_bytes: 169332898 num_examples: 200000 - name: validation num_bytes: 42341854 num_examples: 49999 download_size: 51658907 dataset_size: 423349504 - config_name: irony_identification features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 28178 num_examples: 99 - name: train num_bytes: 22918 num_examples: 80 - name: validation num_bytes: 5260 num_examples: 19 download_size: 27607 dataset_size: 56356 - config_name: kanji_ascii features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 366946 num_examples: 1092 - name: train num_bytes: 293933 num_examples: 875 - name: validation num_bytes: 73013 num_examples: 217 download_size: 317032 dataset_size: 733892 - config_name: kannada features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 140638 num_examples: 316 - name: train num_bytes: 111865 num_examples: 253 - name: validation num_bytes: 28773 num_examples: 63 download_size: 99088 dataset_size: 281276 - config_name: key_value_maps features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 105136 num_examples: 101 - name: train num_bytes: 84317 num_examples: 80 - name: validation num_bytes: 20819 num_examples: 21 download_size: 44793 dataset_size: 210272 - config_name: known_unknowns features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 7960 num_examples: 46 - name: train num_bytes: 5130 num_examples: 30 - name: validation num_bytes: 2830 num_examples: 16 download_size: 20095 dataset_size: 15920 - config_name: language_games features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 979619 num_examples: 2128 - name: train num_bytes: 783111 num_examples: 1704 - name: validation num_bytes: 196508 num_examples: 424 download_size: 377666 dataset_size: 1959238 - config_name: language_identification features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 7376223 num_examples: 10000 - name: train num_bytes: 5908808 num_examples: 8000 - name: validation num_bytes: 1467415 num_examples: 2000 download_size: 5899673 dataset_size: 14752446 - config_name: linguistic_mappings features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 1325186 num_examples: 15527 - name: train num_bytes: 1060088 num_examples: 12426 - name: validation num_bytes: 265098 num_examples: 3101 download_size: 870525 dataset_size: 2650372 - config_name: linguistics_puzzles features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 1746024 num_examples: 2000 - name: train num_bytes: 1398113 num_examples: 1600 - name: validation num_bytes: 347911 num_examples: 400 download_size: 1474730 dataset_size: 3492048 - config_name: logic_grid_puzzle features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 1456218 num_examples: 1000 - name: train num_bytes: 1160137 num_examples: 800 - name: validation num_bytes: 296081 num_examples: 200 download_size: 586520 dataset_size: 2912436 - config_name: logical_args features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 43582 num_examples: 32 - name: train num_bytes: 21072 num_examples: 16 - name: validation num_bytes: 22510 num_examples: 16 download_size: 74073 dataset_size: 87164 - config_name: logical_deduction features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 1056716 num_examples: 1500 - name: train num_bytes: 841788 num_examples: 1200 - name: validation num_bytes: 214928 num_examples: 300 download_size: 148355 dataset_size: 2113432 - config_name: logical_fallacy_detection features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 720286 num_examples: 2800 - name: train num_bytes: 576295 num_examples: 2240 - name: validation num_bytes: 143991 num_examples: 560 download_size: 326385 dataset_size: 1440572 - config_name: logical_sequence features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 22722 num_examples: 39 - name: train num_bytes: 12648 num_examples: 23 - name: validation num_bytes: 10074 num_examples: 16 download_size: 32397 dataset_size: 45444 - config_name: mathematical_induction features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 19018 num_examples: 69 - name: train num_bytes: 14983 num_examples: 53 - name: validation num_bytes: 4035 num_examples: 16 download_size: 22560 dataset_size: 38036 - config_name: matrixshapes features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 1130574 num_examples: 4462 - name: train num_bytes: 906061 num_examples: 3570 - name: validation num_bytes: 224513 num_examples: 892 download_size: 436030 dataset_size: 2261148 - config_name: medical_questions_russian features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 284827 num_examples: 256 - name: train num_bytes: 227802 num_examples: 205 - name: validation num_bytes: 57025 num_examples: 51 download_size: 281643 dataset_size: 569654 - config_name: metaphor_boolean features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 213848 num_examples: 680 - name: train num_bytes: 170765 num_examples: 544 - name: validation num_bytes: 43083 num_examples: 136 download_size: 102463 dataset_size: 427696 - config_name: metaphor_understanding features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 200862 num_examples: 234 - name: train num_bytes: 162101 num_examples: 188 - name: validation num_bytes: 38761 num_examples: 46 download_size: 137229 dataset_size: 401724 - config_name: minute_mysteries_qa features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 3245190 num_examples: 477 - name: train num_bytes: 2623703 num_examples: 383 - name: validation num_bytes: 621487 num_examples: 94 download_size: 3955073 dataset_size: 6490380 - config_name: misconceptions features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 45816 num_examples: 219 - name: train num_bytes: 37246 num_examples: 176 - name: validation num_bytes: 8570 num_examples: 43 download_size: 41069 dataset_size: 91632 - config_name: misconceptions_russian features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 16991 num_examples: 49 - name: train num_bytes: 10970 num_examples: 33 - name: validation num_bytes: 6021 num_examples: 16 download_size: 29961 dataset_size: 33982 - config_name: mnist_ascii features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 61739808 num_examples: 69984 - name: train num_bytes: 49419928 num_examples: 55988 - name: validation num_bytes: 12319880 num_examples: 13996 download_size: 20997609 dataset_size: 123479616 - config_name: modified_arithmetic features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 1220993 num_examples: 6000 - name: train num_bytes: 976859 num_examples: 4800 - name: validation num_bytes: 244134 num_examples: 1200 download_size: 947542 dataset_size: 2441986 - config_name: moral_permissibility features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 162068 num_examples: 342 - name: train num_bytes: 128790 num_examples: 274 - name: validation num_bytes: 33278 num_examples: 68 download_size: 80450 dataset_size: 324136 - config_name: movie_dialog_same_or_different features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 28645997 num_examples: 50000 - name: train num_bytes: 22889061 num_examples: 40000 - name: validation num_bytes: 5756936 num_examples: 10000 download_size: 19923333 dataset_size: 57291994 - config_name: movie_recommendation features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 173557 num_examples: 500 - name: train num_bytes: 138936 num_examples: 400 - name: validation num_bytes: 34621 num_examples: 100 download_size: 151639 dataset_size: 347114 - config_name: mult_data_wrangling features: - name: idx dtype: int32 - name: inputs dtype: string - name: targets sequence: string - name: multiple_choice_targets sequence: string - name: multiple_choice_scores sequence: int32 splits: - name: default num_bytes: 625422 num_examples: 7854 - name: train num_bytes: 507838 num_examples: 6380 - name: validation num_bytes: 117584 num_examples: 1474 download_size: 260725 dataset_size: 1250844 configs: - config_name: abstract_narrative_understanding data_files: - split: default path: abstract_narrative_understanding/default-* - split: train path: abstract_narrative_understanding/train-* - split: validation path: abstract_narrative_understanding/validation-* - config_name: anachronisms data_files: - split: default path: anachronisms/default-* - split: train path: anachronisms/train-* - split: validation path: anachronisms/validation-* - config_name: analogical_similarity data_files: - split: default path: analogical_similarity/default-* - split: train path: analogical_similarity/train-* - split: validation path: analogical_similarity/validation-* - config_name: analytic_entailment data_files: - split: default path: analytic_entailment/default-* - split: train path: analytic_entailment/train-* - split: validation path: analytic_entailment/validation-* - config_name: arithmetic data_files: - split: default path: arithmetic/default-* - split: train path: arithmetic/train-* - split: validation path: arithmetic/validation-* - config_name: ascii_word_recognition data_files: - split: default path: ascii_word_recognition/default-* - split: train path: ascii_word_recognition/train-* - split: validation path: ascii_word_recognition/validation-* - config_name: authorship_verification data_files: - split: default path: authorship_verification/default-* - split: train path: authorship_verification/train-* - split: validation path: authorship_verification/validation-* - config_name: auto_categorization data_files: - split: default path: auto_categorization/default-* - split: train path: auto_categorization/train-* - split: validation path: auto_categorization/validation-* - config_name: auto_debugging data_files: - split: default path: auto_debugging/default-* - split: train path: auto_debugging/train-* - split: validation path: auto_debugging/validation-* - config_name: bbq_lite_json data_files: - split: default path: bbq_lite_json/default-* - split: train path: bbq_lite_json/train-* - split: validation path: bbq_lite_json/validation-* - config_name: bridging_anaphora_resolution_barqa data_files: - split: default path: bridging_anaphora_resolution_barqa/default-* - split: train path: bridging_anaphora_resolution_barqa/train-* - split: validation path: bridging_anaphora_resolution_barqa/validation-* - config_name: causal_judgment data_files: - split: default path: causal_judgment/default-* - split: train path: causal_judgment/train-* - split: validation path: causal_judgment/validation-* - config_name: cause_and_effect data_files: - split: default path: cause_and_effect/default-* - split: train path: cause_and_effect/train-* - split: validation path: cause_and_effect/validation-* - config_name: checkmate_in_one data_files: - split: default path: checkmate_in_one/default-* - split: train path: checkmate_in_one/train-* - split: validation path: checkmate_in_one/validation-* - config_name: chess_state_tracking data_files: - split: default path: chess_state_tracking/default-* - split: train path: chess_state_tracking/train-* - split: validation path: chess_state_tracking/validation-* - config_name: chinese_remainder_theorem data_files: - split: default path: chinese_remainder_theorem/default-* - split: train path: chinese_remainder_theorem/train-* - split: validation path: chinese_remainder_theorem/validation-* - config_name: cifar10_classification data_files: - split: default path: cifar10_classification/default-* - split: train path: cifar10_classification/train-* - split: validation path: cifar10_classification/validation-* - config_name: code_line_description data_files: - split: default path: code_line_description/default-* - split: train path: code_line_description/train-* - split: validation path: code_line_description/validation-* - config_name: codenames data_files: - split: default path: codenames/default-* - split: train path: codenames/train-* - split: validation path: codenames/validation-* - config_name: color data_files: - split: default path: color/default-* - split: train path: color/train-* - split: validation path: color/validation-* - config_name: common_morpheme data_files: - split: default path: common_morpheme/default-* - split: train path: common_morpheme/train-* - split: validation path: common_morpheme/validation-* - config_name: conceptual_combinations data_files: - split: default path: conceptual_combinations/default-* - split: train path: conceptual_combinations/train-* - split: validation path: conceptual_combinations/validation-* - config_name: conlang_translation data_files: - split: default path: conlang_translation/default-* - split: train path: conlang_translation/train-* - split: validation path: conlang_translation/validation-* - config_name: contextual_parametric_knowledge_conflicts data_files: - split: default path: contextual_parametric_knowledge_conflicts/default-* - split: train path: contextual_parametric_knowledge_conflicts/train-* - split: validation path: contextual_parametric_knowledge_conflicts/validation-* - config_name: crash_blossom data_files: - split: default path: crash_blossom/default-* - split: train path: crash_blossom/train-* - split: validation path: crash_blossom/validation-* - config_name: crass_ai data_files: - split: default path: crass_ai/default-* - split: train path: crass_ai/train-* - split: validation path: crass_ai/validation-* - config_name: cryobiology_spanish data_files: - split: default path: cryobiology_spanish/default-* - split: train path: cryobiology_spanish/train-* - split: validation path: cryobiology_spanish/validation-* - config_name: cryptonite data_files: - split: default path: cryptonite/default-* - split: train path: cryptonite/train-* - split: validation path: cryptonite/validation-* - config_name: cs_algorithms data_files: - split: default path: cs_algorithms/default-* - split: train path: cs_algorithms/train-* - split: validation path: cs_algorithms/validation-* - config_name: dark_humor_detection data_files: - split: default path: dark_humor_detection/default-* - split: train path: dark_humor_detection/train-* - split: validation path: dark_humor_detection/validation-* - config_name: date_understanding data_files: - split: default path: date_understanding/default-* - split: train path: date_understanding/train-* - split: validation path: date_understanding/validation-* - config_name: disambiguation_qa data_files: - split: default path: disambiguation_qa/default-* - split: train path: disambiguation_qa/train-* - split: validation path: disambiguation_qa/validation-* - config_name: discourse_marker_prediction data_files: - split: default path: discourse_marker_prediction/default-* - split: train path: discourse_marker_prediction/train-* - split: validation path: discourse_marker_prediction/validation-* - config_name: disfl_qa data_files: - split: default path: disfl_qa/default-* - split: train path: disfl_qa/train-* - split: validation path: disfl_qa/validation-* - config_name: dyck_languages data_files: - split: default path: dyck_languages/default-* - split: train path: dyck_languages/train-* - split: validation path: dyck_languages/validation-* - config_name: elementary_math_qa data_files: - split: default path: elementary_math_qa/default-* - split: train path: elementary_math_qa/train-* - split: validation path: elementary_math_qa/validation-* - config_name: emoji_movie data_files: - split: default path: emoji_movie/default-* - split: train path: emoji_movie/train-* - split: validation path: emoji_movie/validation-* - config_name: emojis_emotion_prediction data_files: - split: default path: emojis_emotion_prediction/default-* - split: train path: emojis_emotion_prediction/train-* - split: validation path: emojis_emotion_prediction/validation-* - config_name: empirical_judgments data_files: - split: default path: empirical_judgments/default-* - split: train path: empirical_judgments/train-* - split: validation path: empirical_judgments/validation-* - config_name: english_proverbs data_files: - split: default path: english_proverbs/default-* - split: train path: english_proverbs/train-* - split: validation path: english_proverbs/validation-* - config_name: english_russian_proverbs data_files: - split: default path: english_russian_proverbs/default-* - split: train path: english_russian_proverbs/train-* - split: validation path: english_russian_proverbs/validation-* - config_name: entailed_polarity data_files: - split: default path: entailed_polarity/default-* - split: train path: entailed_polarity/train-* - split: validation path: entailed_polarity/validation-* - config_name: entailed_polarity_hindi data_files: - split: default path: entailed_polarity_hindi/default-* - split: train path: entailed_polarity_hindi/train-* - split: validation path: entailed_polarity_hindi/validation-* - config_name: epistemic_reasoning data_files: - split: default path: epistemic_reasoning/default-* - split: train path: epistemic_reasoning/train-* - split: validation path: epistemic_reasoning/validation-* - config_name: evaluating_information_essentiality data_files: - split: default path: evaluating_information_essentiality/default-* - split: train path: evaluating_information_essentiality/train-* - split: validation path: evaluating_information_essentiality/validation-* - config_name: fact_checker data_files: - split: default path: fact_checker/default-* - split: train path: fact_checker/train-* - split: validation path: fact_checker/validation-* - config_name: fantasy_reasoning data_files: - split: default path: fantasy_reasoning/default-* - split: train path: fantasy_reasoning/train-* - split: validation path: fantasy_reasoning/validation-* - config_name: few_shot_nlg data_files: - split: default path: few_shot_nlg/default-* - split: train path: few_shot_nlg/train-* - split: validation path: few_shot_nlg/validation-* - config_name: figure_of_speech_detection data_files: - split: default path: figure_of_speech_detection/default-* - split: train path: figure_of_speech_detection/train-* - split: validation path: figure_of_speech_detection/validation-* - config_name: formal_fallacies_syllogisms_negation data_files: - split: default path: formal_fallacies_syllogisms_negation/default-* - split: train path: formal_fallacies_syllogisms_negation/train-* - split: validation path: formal_fallacies_syllogisms_negation/validation-* - config_name: gem data_files: - split: default path: gem/default-* - split: train path: gem/train-* - split: validation path: gem/validation-* - config_name: gender_inclusive_sentences_german data_files: - split: default path: gender_inclusive_sentences_german/default-* - split: train path: gender_inclusive_sentences_german/train-* - split: validation path: gender_inclusive_sentences_german/validation-* - config_name: general_knowledge data_files: - split: default path: general_knowledge/default-* - split: train path: general_knowledge/train-* - split: validation path: general_knowledge/validation-* - config_name: geometric_shapes data_files: - split: default path: geometric_shapes/default-* - split: train path: geometric_shapes/train-* - split: validation path: geometric_shapes/validation-* - config_name: goal_step_wikihow data_files: - split: default path: goal_step_wikihow/default-* - split: train path: goal_step_wikihow/train-* - split: validation path: goal_step_wikihow/validation-* - config_name: gre_reading_comprehension data_files: - split: default path: gre_reading_comprehension/default-* - split: train path: gre_reading_comprehension/train-* - split: validation path: gre_reading_comprehension/validation-* - config_name: hhh_alignment data_files: - split: default path: hhh_alignment/default-* - split: train path: hhh_alignment/train-* - split: validation path: hhh_alignment/validation-* - config_name: hindi_question_answering data_files: - split: default path: hindi_question_answering/default-* - split: train path: hindi_question_answering/train-* - split: validation path: hindi_question_answering/validation-* - config_name: hindu_knowledge data_files: - split: default path: hindu_knowledge/default-* - split: train path: hindu_knowledge/train-* - split: validation path: hindu_knowledge/validation-* - config_name: hinglish_toxicity data_files: - split: default path: hinglish_toxicity/default-* - split: train path: hinglish_toxicity/train-* - split: validation path: hinglish_toxicity/validation-* - config_name: human_organs_senses data_files: - split: default path: human_organs_senses/default-* - split: train path: human_organs_senses/train-* - split: validation path: human_organs_senses/validation-* - config_name: hyperbaton data_files: - split: default path: hyperbaton/default-* - split: train path: hyperbaton/train-* - split: validation path: hyperbaton/validation-* - config_name: identify_math_theorems data_files: - split: default path: identify_math_theorems/default-* - split: train path: identify_math_theorems/train-* - split: validation path: identify_math_theorems/validation-* - config_name: identify_odd_metaphor data_files: - split: default path: identify_odd_metaphor/default-* - split: train path: identify_odd_metaphor/train-* - split: validation path: identify_odd_metaphor/validation-* - config_name: implicatures data_files: - split: default path: implicatures/default-* - split: train path: implicatures/train-* - split: validation path: implicatures/validation-* - config_name: implicit_relations data_files: - split: default path: implicit_relations/default-* - split: train path: implicit_relations/train-* - split: validation path: implicit_relations/validation-* - config_name: indic_cause_and_effect data_files: - split: default path: indic_cause_and_effect/default-* - split: train path: indic_cause_and_effect/train-* - split: validation path: indic_cause_and_effect/validation-* - config_name: intent_recognition data_files: - split: default path: intent_recognition/default-* - split: train path: intent_recognition/train-* - split: validation path: intent_recognition/validation-* - config_name: international_phonetic_alphabet_nli data_files: - split: default path: international_phonetic_alphabet_nli/default-* - split: train path: international_phonetic_alphabet_nli/train-* - split: validation path: international_phonetic_alphabet_nli/validation-* - config_name: international_phonetic_alphabet_transliterate data_files: - split: default path: international_phonetic_alphabet_transliterate/default-* - split: train path: international_phonetic_alphabet_transliterate/train-* - split: validation path: international_phonetic_alphabet_transliterate/validation-* - config_name: intersect_geometry data_files: - split: default path: intersect_geometry/default-* - split: train path: intersect_geometry/train-* - split: validation path: intersect_geometry/validation-* - config_name: irony_identification data_files: - split: default path: irony_identification/default-* - split: train path: irony_identification/train-* - split: validation path: irony_identification/validation-* - config_name: kanji_ascii data_files: - split: default path: kanji_ascii/default-* - split: train path: kanji_ascii/train-* - split: validation path: kanji_ascii/validation-* - config_name: kannada data_files: - split: default path: kannada/default-* - split: train path: kannada/train-* - split: validation path: kannada/validation-* - config_name: key_value_maps data_files: - split: default path: key_value_maps/default-* - split: train path: key_value_maps/train-* - split: validation path: key_value_maps/validation-* - config_name: known_unknowns data_files: - split: default path: known_unknowns/default-* - split: train path: known_unknowns/train-* - split: validation path: known_unknowns/validation-* - config_name: language_games data_files: - split: default path: language_games/default-* - split: train path: language_games/train-* - split: validation path: language_games/validation-* - config_name: language_identification data_files: - split: default path: language_identification/default-* - split: train path: language_identification/train-* - split: validation path: language_identification/validation-* - config_name: linguistic_mappings data_files: - split: default path: linguistic_mappings/default-* - split: train path: linguistic_mappings/train-* - split: validation path: linguistic_mappings/validation-* - config_name: linguistics_puzzles data_files: - split: default path: linguistics_puzzles/default-* - split: train path: linguistics_puzzles/train-* - split: validation path: linguistics_puzzles/validation-* - config_name: logic_grid_puzzle data_files: - split: default path: logic_grid_puzzle/default-* - split: train path: logic_grid_puzzle/train-* - split: validation path: logic_grid_puzzle/validation-* - config_name: logical_args data_files: - split: default path: logical_args/default-* - split: train path: logical_args/train-* - split: validation path: logical_args/validation-* - config_name: logical_deduction data_files: - split: default path: logical_deduction/default-* - split: train path: logical_deduction/train-* - split: validation path: logical_deduction/validation-* - config_name: logical_fallacy_detection data_files: - split: default path: logical_fallacy_detection/default-* - split: train path: logical_fallacy_detection/train-* - split: validation path: logical_fallacy_detection/validation-* - config_name: logical_sequence data_files: - split: default path: logical_sequence/default-* - split: train path: logical_sequence/train-* - split: validation path: logical_sequence/validation-* - config_name: mathematical_induction data_files: - split: default path: mathematical_induction/default-* - split: train path: mathematical_induction/train-* - split: validation path: mathematical_induction/validation-* - config_name: matrixshapes data_files: - split: default path: matrixshapes/default-* - split: train path: matrixshapes/train-* - split: validation path: matrixshapes/validation-* - config_name: medical_questions_russian data_files: - split: default path: medical_questions_russian/default-* - split: train path: medical_questions_russian/train-* - split: validation path: medical_questions_russian/validation-* - config_name: metaphor_boolean data_files: - split: default path: metaphor_boolean/default-* - split: train path: metaphor_boolean/train-* - split: validation path: metaphor_boolean/validation-* - config_name: metaphor_understanding data_files: - split: default path: metaphor_understanding/default-* - split: train path: metaphor_understanding/train-* - split: validation path: metaphor_understanding/validation-* - config_name: minute_mysteries_qa data_files: - split: default path: minute_mysteries_qa/default-* - split: train path: minute_mysteries_qa/train-* - split: validation path: minute_mysteries_qa/validation-* - config_name: misconceptions data_files: - split: default path: misconceptions/default-* - split: train path: misconceptions/train-* - split: validation path: misconceptions/validation-* - config_name: misconceptions_russian data_files: - split: default path: misconceptions_russian/default-* - split: train path: misconceptions_russian/train-* - split: validation path: misconceptions_russian/validation-* - config_name: mnist_ascii data_files: - split: default path: mnist_ascii/default-* - split: train path: mnist_ascii/train-* - split: validation path: mnist_ascii/validation-* - config_name: modified_arithmetic data_files: - split: default path: modified_arithmetic/default-* - split: train path: modified_arithmetic/train-* - split: validation path: modified_arithmetic/validation-* - config_name: moral_permissibility data_files: - split: default path: moral_permissibility/default-* - split: train path: moral_permissibility/train-* - split: validation path: moral_permissibility/validation-* - config_name: movie_dialog_same_or_different data_files: - split: default path: movie_dialog_same_or_different/default-* - split: train path: movie_dialog_same_or_different/train-* - split: validation path: movie_dialog_same_or_different/validation-* - config_name: movie_recommendation data_files: - split: default path: movie_recommendation/default-* - split: train path: movie_recommendation/train-* - split: validation path: movie_recommendation/validation-* - config_name: mult_data_wrangling data_files: - split: default path: mult_data_wrangling/default-* - split: train path: mult_data_wrangling/train-* - split: validation path: mult_data_wrangling/validation-* ---
提供机构：
kowndinya23
原始信息汇总

数据集概述

1. abstract_narrative_understanding

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 3000 examples, 6560069 bytes
    • train: 2400 examples, 5249819 bytes
    • validation: 600 examples, 1310250 bytes
  • 下载大小: 1435670 bytes
  • 数据集大小: 13120138 bytes

2. anachronisms

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 230 examples, 48826 bytes
    • train: 184 examples, 39116 bytes
    • validation: 46 examples, 9710 bytes
  • 下载大小: 40931 bytes
  • 数据集大小: 97652 bytes

3. analogical_similarity

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 323 examples, 1373815 bytes
    • train: 259 examples, 1101512 bytes
    • validation: 64 examples, 272303 bytes
  • 下载大小: 285403 bytes
  • 数据集大小: 2747630 bytes

4. analytic_entailment

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 70 examples, 17316 bytes
    • train: 54 examples, 13368 bytes
    • validation: 16 examples, 3948 bytes
  • 下载大小: 21156 bytes
  • 数据集大小: 34632 bytes

5. arithmetic

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 15023 examples, 3833272 bytes
    • train: 12019 examples, 3066775 bytes
    • validation: 3004 examples, 766497 bytes
  • 下载大小: 2777853 bytes
  • 数据集大小: 7666544 bytes

6. ascii_word_recognition

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 5000 examples, 4984662 bytes
    • train: 4000 examples, 3997273 bytes
    • validation: 1000 examples, 987389 bytes
  • 下载大小: 2290165 bytes
  • 数据集大小: 9969324 bytes

7. authorship_verification

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 880 examples, 14118592 bytes
    • train: 704 examples, 11288481 bytes
    • validation: 176 examples, 2830111 bytes
  • 下载大小: 17714673 bytes
  • 数据集大小: 28237184 bytes

8. auto_categorization

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 328 examples, 40549 bytes
    • train: 263 examples, 32992 bytes
    • validation: 65 examples, 7557 bytes
  • 下载大小: 50064 bytes
  • 数据集大小: 81098 bytes

9. auto_debugging

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 34 examples, 5284 bytes
    • train: 18 examples, 2763 bytes
    • validation: 16 examples, 2521 bytes
  • 下载大小: 16180 bytes
  • 数据集大小: 10568 bytes

10. bbq_lite_json

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 16076 examples, 6890493 bytes
    • train: 12866 examples, 5508584 bytes
    • validation: 3210 examples, 1381909 bytes
  • 下载大小: 2208854 bytes
  • 数据集大小: 13780986 bytes

11. bridging_anaphora_resolution_barqa

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 648 examples, 1971015 bytes
    • train: 519 examples, 1537264 bytes
    • validation: 129 examples, 433751 bytes
  • 下载大小: 2143230 bytes
  • 数据集大小: 3942030 bytes

12. causal_judgment

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 190 examples, 204878 bytes
    • train: 152 examples, 164940 bytes
    • validation: 38 examples, 39938 bytes
  • 下载大小: 136495 bytes
  • 数据集大小: 409756 bytes

13. cause_and_effect

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 153 examples, 49314 bytes
    • train: 123 examples, 39620 bytes
    • validation: 30 examples, 9694 bytes
  • 下载大小: 37016 bytes
  • 数据集大小: 98628 bytes

14. checkmate_in_one

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 3498 examples, 3123256 bytes
    • train: 2799 examples, 2502314 bytes
    • validation: 699 examples, 620942 bytes
  • 下载大小: 2227113 bytes
  • 数据集大小: 6246512 bytes

15. chess_state_tracking

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 6000 examples, 3269932 bytes
    • train: 4800 examples, 2616294 bytes
    • validation: 1200 examples, 653638 bytes
  • 下载大小: 2064226 bytes
  • 数据集大小: 6539864 bytes

16. chinese_remainder_theorem

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 500 examples, 153222 bytes
    • train: 400 examples, 122601 bytes
    • validation: 100 examples, 30621 bytes
  • 下载大小: 85693 bytes
  • 数据集大小: 306444 bytes

17. cifar10_classification

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 20000 examples, 111022200 bytes
    • train: 16000 examples, 88782724 bytes
    • validation: 4000 examples, 22239476 bytes
  • 下载大小: 179818834 bytes
  • 数据集大小: 222044400 bytes

18. code_line_description

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 60 examples, 33670 bytes
    • train: 44 examples, 25530 bytes
    • validation: 16 examples, 8140 bytes
  • 下载大小: 42348 bytes
  • 数据集大小: 67340 bytes

19. codenames

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 85 examples, 25195 bytes
    • train: 68 examples, 19964 bytes
    • validation: 17 examples, 5231 bytes
  • 下载大小: 31257 bytes
  • 数据集大小: 50390 bytes

20. color

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 4000 examples, 1633263 bytes
    • train: 3200 examples, 1306663 bytes
    • validation: 800 examples, 326600 bytes
  • 下载大小: 301045 bytes
  • 数据集大小: 3266526 bytes

21. common_morpheme

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 50 examples, 12388 bytes
    • train: 34 examples, 8444 bytes
    • validation: 16 examples, 3944 bytes
  • 下载大小: 25122 bytes
  • 数据集大小: 24776 bytes

22. conceptual_combinations

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 103 examples, 58859 bytes
    • train: 84 examples, 48010 bytes
    • validation: 19 examples, 10849 bytes
  • 下载大小: 72767 bytes
  • 数据集大小: 117718 bytes

23. conlang_translation

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 164 examples, 215190 bytes
    • train: 132 examples, 173024 bytes
    • validation: 32 examples, 42166 bytes
  • 下载大小: 78115 bytes
  • 数据集大小: 430380 bytes

24. contextual_parametric_knowledge_conflicts

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 17528 examples, 14587554 bytes
    • train: 14023 examples, 11666236 bytes
    • validation: 3505 examples, 2921318 bytes
  • 下载大小: 16791080 bytes
  • 数据集大小: 29175108 bytes

25. crash_blossom

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 38 examples, 12194 bytes
    • train: 22 examples, 6999 bytes
    • validation: 16 examples, 5195 bytes
  • 下载大小: 19382 bytes
  • 数据集大小: 24388 bytes

26. crass_ai

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
    • multiple_choice_scores: sequence: int32
  • 分割:
    • default: 44 examples, 22870 bytes
    • train: 28 examples, 14130 bytes
    • validation: 16 examples, 8740 bytes
  • 下载大小: 35821 bytes
  • 数据集大小: 45740 bytes

27. cryobiology_spanish

  • 特征:
    • idx: int32
    • inputs: string
    • targets: sequence: string
    • multiple_choice_targets: sequence: string
5,000+
优质数据集
54 个
任务类型
进入经典数据集
关于我们
遇见数据集——让每个数据集都被发现，让每一次遇见都有价值。
数发科官网www.sfktec.com.cn
联系我们
youjian
selectdataset@iotsh.com.cn
商业合作
数据驱动未来，携手共赢发展
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作